ChatDev/MultiAgentEbook/papers.csv

1	Title	Authors	Date	Abstract	Url	AwesomeListCategory	Categories	PaperIndex	Affiliation
2	(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts	Minghao Wu, Yulin Yuan, Gholamreza Haffari, Longyue Wang	2024.5.20	Recent advancements in machine translation (MT) have significantly enhanced translation quality across various domains. However, the translation of literary texts remains a formidable challenge due to their complex language, figurative ex- pressions, and cultural nuances. In this work, we introduce a novel multi-agent framework based on large language models (LLMs) for literary translation, im- plemented as a company called TRANSAGENTS, which mirrors traditional trans- lation publication process by leveraging the collective capabilities of multiple agents, to address the intricate demands of translating literary works. To evaluate the effectiveness of our system, we propose two innovative evaluation strategies: Monolingual Human Preference (MHP) and Bilingual LLM Preference (BLP). MHP assesses translations from the perspective of monolingual readers of the tar- get language, while BLP uses advanced LLMs to compare translations directly with the original texts. Empirical findings indicate that despite lower d-BLEU scores, translations from TRANSAGENTS are preferred by both human evalua- tors and LLMs over human-written references, particularly in genres requiring domain-specific knowledge. We also highlight the strengths and limitations of TRANSAGENTS through case studies and suggests directions for future research.	https://arxiv.org/abs/2405.11804	Organization	Computation and Language (cs.CL)	(perhaps)_beyond_human_translation_20240520	Monash University, University of Macau, Tencent AI Lab
3	(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts	Minghao Wu, Yulin Yuan, Gholamreza Haffari, Longyue Wang	2024.5.20	Recent advancements in machine translation (MT) have significantly enhanced translation quality across various domains. However, the translation of literary texts remains a formidable challenge due to their complex language, figurative ex- pressions, and cultural nuances. In this work, we introduce a novel multi-agent framework based on large language models (LLMs) for literary translation, im- plemented as a company called TRANSAGENTS, which mirrors traditional trans- lation publication process by leveraging the collective capabilities of multiple agents, to address the intricate demands of translating literary works. To evaluate the effectiveness of our system, we propose two innovative evaluation strategies: Monolingual Human Preference (MHP) and Bilingual LLM Preference (BLP). MHP assesses translations from the perspective of monolingual readers of the tar- get language, while BLP uses advanced LLMs to compare translations directly with the original texts. Empirical findings indicate that despite lower d-BLEU scores, translations from TRANSAGENTS are preferred by both human evalua- tors and LLMs over human-written references, particularly in genres requiring domain-specific knowledge. We also highlight the strengths and limitations of TRANSAGENTS through case studies and suggests directions for future research.	https://arxiv.org/abs/2405.11804	Simulation	Computation and Language (cs.CL)	(perhaps)_beyond_human_translation_20240520	Monash University, University of Macau, Tencent AI Lab
4	360°REA: Towards A Reusable Experience Accumulation with 360° Assessment for Multi-Agent System	Shen Gao, Hao Li, Zhengliang Shi, Chengrui Huang, Quan Tu, Zhiliang Tian, Minlie Huang, Shuo Shang	2024.4.8	Large language model agents have demonstrated remarkable advancements across various complex tasks. Recent works focus on optimizing the agent team or employing self-reflection to iteratively solve complex tasks. Since these agents are all based on the same LLM, only conducting self-evaluation or removing underperforming agents does not substantively enhance the capability of the agents. We argue that a comprehensive evaluation and accumulating experience from evaluation feedback is an effective approach to improving system performance. In this paper, we propose Reusable Experience Accumulation with 360◦ Assessment (360◦REA), a hierarchical multi-agent framework inspired by corporate organizational practices. The framework employs a novel 360◦ performance assessment method for multi-perspective performance evaluation with fine-grained assessment. To enhance the capability of agents in addressing complex tasks, we introduce dual-level experience pool for agents to accumulate experience through fine-grained assessment. Extensive experiments on complex task datasets demonstrate the effectiveness of 360◦REA.	https://arxiv.org/abs/2404.05569	Evolution	Artificial Intelligence (cs.AI)	360°rea_towards_a_reusable_20240408	University of Electronic Science and Technology of China, Shandong University, Renmin University of China, National University of Defense Technology, Tsinghua University
5	Affordable Generative Agents	Yangbin Yu, Qin Zhang, Junyou Li, Qiang Fu, Deheng Ye	2024.2.3	The emergence of large language models (LLMs) has significantly advanced the simulation of believable interactive agents. However, the substantial cost on maintaining the prolonged agent interactions poses challenge over the deployment of believable LLM-based agents. Therefore, in this paper, we develop Affordable Generative Agents (AGA), a framework for enabling the generation of believable and low-cost interactions on both agent-environment and inter-agents levels. Specifically, for agent- environment interactions, we substitute repetitive LLM inferences with learned policies; while for inter-agent interactions, we model the social rela- tionships between agents and compress auxiliary dialogue information. Extensive experiments on multiple environments show the effectiveness and efficiency of our proposed framework. Also, we delve into the mechanisms of emergent believable behaviors lying in LLM agents, demonstrating that agents can only generate finite behaviors in fixed environments, based upon which, we understand ways to facilitate emergent interaction behaviors. Our code is publicly available at: https://github. com/AffordableGenerativeAgents/ Affordable-Generative-Agents.	https://arxiv.org/abs/2402.02053	Evolution	Artificial Intelligence (cs.AI)	affordable_generative_agents_20240203	Tencent Inc.
6	Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents	Junkai Li, Siyu Wang, Meng Zhang, Weitao Li, Yunghwei Lai, Xinhui Kang, Weizhi Ma, Yang Liu	2024.5.5	In this paper, we introduce a simulacrum of hospital called Agent Hospital that simulates the entire process of treating illness. All patients, nurses, and doctors are autonomous agents powered by large language models (LLMs). Our central goal is to enable a doctor agent to learn how to treat illness within the simulacrum. To do so, we propose a method called MedAgent-Zero. As the simulacrum can simulate disease onset and progression based on knowledge bases and LLMs, doctor agents can keep accumulating experience from both successful and unsuccessful cases. Simulation experiments show that the treatment performance of doctor agents consistently improves on various tasks. More interestingly, the knowledge the doctor agents have acquired in Agent Hospital is applicable to real-world medicare benchmarks. After treating around ten thousand patients (real-world doctors may take over two years), the evolved doctor agent achieves a state-of-the-art accuracy of 9	https://arxiv.org/abs/2405.02957	Evolution	Artificial Intelligence (cs.AI)	agent_hospital_a_simulacrum_20240505	Tsinghua University
7	Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents	Junkai Li, Siyu Wang, Meng Zhang, Weitao Li, Yunghwei Lai, Xinhui Kang, Weizhi Ma, Yang Liu	2024.5.5	In this paper, we introduce a simulacrum of hospital called Agent Hospital that simulates the entire process of treating illness. All patients, nurses, and doctors are autonomous agents powered by large language models (LLMs). Our central goal is to enable a doctor agent to learn how to treat illness within the simulacrum. To do so, we propose a method called MedAgent-Zero. As the simulacrum can simulate disease onset and progression based on knowledge bases and LLMs, doctor agents can keep accumulating experience from both successful and unsuccessful cases. Simulation experiments show that the treatment performance of doctor agents consistently improves on various tasks. More interestingly, the knowledge the doctor agents have acquired in Agent Hospital is applicable to real-world medicare benchmarks. After treating around ten thousand patients (real-world doctors may take over two years), the evolved doctor agent achieves a state-of-the-art accuracy of 9	https://arxiv.org/abs/2405.02957	Organization	Artificial Intelligence (cs.AI)	agent_hospital_a_simulacrum_20240505	Tsinghua University
8	Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents	Junkai Li, Siyu Wang, Meng Zhang, Weitao Li, Yunghwei Lai, Xinhui Kang, Weizhi Ma, Yang Liu	2024.5.5	In this paper, we introduce a simulacrum of hospital called Agent Hospital that simulates the entire process of treating illness. All patients, nurses, and doctors are autonomous agents powered by large language models (LLMs). Our central goal is to enable a doctor agent to learn how to treat illness within the simulacrum. To do so, we propose a method called MedAgent-Zero. As the simulacrum can simulate disease onset and progression based on knowledge bases and LLMs, doctor agents can keep accumulating experience from both successful and unsuccessful cases. Simulation experiments show that the treatment performance of doctor agents consistently improves on various tasks. More interestingly, the knowledge the doctor agents have acquired in Agent Hospital is applicable to real-world medicare benchmarks. After treating around ten thousand patients (real-world doctors may take over two years), the evolved doctor agent achieves a state-of-the-art accuracy of 9	https://arxiv.org/abs/2405.02957	Simulation	Artificial Intelligence (cs.AI)	agent_hospital_a_simulacrum_20240505	Tsinghua University
9	AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems	Junjie Zhang, Yupeng Hou, Ruobing Xie, Wenqi Sun, Julian McAuley, Wayne Xin Zhao, Leyu Lin, Ji-Rong Wen	2023.10.13	Recently, there has been an emergence of employing LLM-powered agents as believable human proxies, based on their remarkable decision-making capability. However, existing studies mainly focus on simulating human dialogue. Human non-verbal behaviors, such as item clicking in recommender systems, although implicitly ex- hibiting user preferences and could enhance the modeling of users, have not been deeply explored. The main reasons lie in the gap between language modeling and behavior modeling, as well as the incomprehension of LLMs about user-item relations. To address this issue, we propose AgentCF for simulating user- item interactions in recommender systems through agent-based collaborative filtering. We creatively consider not only users but also items as agents, and develop a collaborative learning approach that optimizes both kinds of agents together. Specifically, at each time step, we first prompt the user and item agents to interact au- tonomously. Then, based on the disparities between the agents’ decisions and real-world interaction records, user and item agents are prompted to reflect on and adjust the misleading simulations collaboratively, thereby modeling their two-sided relations. The op- timized agents can also propagate their preferences to other agents in subsequent interactions, implicitly capturing the collaborative fil- tering idea. Overall, the optimized agents exhibit diverse interaction behaviors within our framework, including user-item, user-user, item-item, and collective interactions. The results show that these agents can demonstrate personalized behaviors akin to those of real- world individuals, sparking the development of next-generation user behavior simulation.	https://arxiv.org/abs/2310.09233	Communication	Information Retrieval (cs.IR)	agentcf_collaborative_learning_with_20231013	Renmin University of China, UC San Diego, Tencent
10	AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems	Junjie Zhang, Yupeng Hou, Ruobing Xie, Wenqi Sun, Julian McAuley, Wayne Xin Zhao, Leyu Lin, Ji-Rong Wen	2023.10.13	Recently, there has been an emergence of employing LLM-powered agents as believable human proxies, based on their remarkable decision-making capability. However, existing studies mainly focus on simulating human dialogue. Human non-verbal behaviors, such as item clicking in recommender systems, although implicitly ex- hibiting user preferences and could enhance the modeling of users, have not been deeply explored. The main reasons lie in the gap between language modeling and behavior modeling, as well as the incomprehension of LLMs about user-item relations. To address this issue, we propose AgentCF for simulating user- item interactions in recommender systems through agent-based collaborative filtering. We creatively consider not only users but also items as agents, and develop a collaborative learning approach that optimizes both kinds of agents together. Specifically, at each time step, we first prompt the user and item agents to interact au- tonomously. Then, based on the disparities between the agents’ decisions and real-world interaction records, user and item agents are prompted to reflect on and adjust the misleading simulations collaboratively, thereby modeling their two-sided relations. The op- timized agents can also propagate their preferences to other agents in subsequent interactions, implicitly capturing the collaborative fil- tering idea. Overall, the optimized agents exhibit diverse interaction behaviors within our framework, including user-item, user-user, item-item, and collective interactions. The results show that these agents can demonstrate personalized behaviors akin to those of real- world individuals, sparking the development of next-generation user behavior simulation.	https://arxiv.org/abs/2310.09233	Simulation	Information Retrieval (cs.IR)	agentcf_collaborative_learning_with_20231013	Renmin University of China, UC San Diego, Tencent
11	AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors	Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, Yujia Qin, Xin Cong, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou	2023.8.21	Autonomous agents empowered by Large Language Models (LLMs) have under- gone significant improvements, enabling them to generalize across a broad spec- trum of tasks. However, in real-world scenarios, cooperation among individuals is often required to enhance the efficiency and effectiveness of task accomplishment. Hence, inspired by human group dynamics, we propose a multi-agent framework AGENTVERSE that can effectively orchestrate a collaborative group of expert agents as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that AGENTVERSE can proficiently deploy multi-agent groups that outperform a single agent. Extensive experiments on text understanding, reasoning, coding, tool utiliza- tion, and embodied AI confirm the effectiveness of AGENTVERSE. Moreover, our analysis of agent interactions within AGENTVERSE reveals the emergence of spe- cific collaborative behaviors, contributing to heightened group efficiency. Our code has been released at https://github.com/OpenBMB/AgentVerse/.	https://arxiv.org/abs/2308.10848	Communication	Computation and Language (cs.CL)	agentverse_facilitating_multi-agent_collaboration_20230821	Tsinghua University, Beijing University of Posts and Telecommunications, Tencent Inc.
12	AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors	Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, Yujia Qin, Xin Cong, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou	2023.8.21	Autonomous agents empowered by Large Language Models (LLMs) have under- gone significant improvements, enabling them to generalize across a broad spec- trum of tasks. However, in real-world scenarios, cooperation among individuals is often required to enhance the efficiency and effectiveness of task accomplishment. Hence, inspired by human group dynamics, we propose a multi-agent framework AGENTVERSE that can effectively orchestrate a collaborative group of expert agents as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that AGENTVERSE can proficiently deploy multi-agent groups that outperform a single agent. Extensive experiments on text understanding, reasoning, coding, tool utiliza- tion, and embodied AI confirm the effectiveness of AGENTVERSE. Moreover, our analysis of agent interactions within AGENTVERSE reveals the emergence of spe- cific collaborative behaviors, contributing to heightened group efficiency. Our code has been released at https://github.com/OpenBMB/AgentVerse/.	https://arxiv.org/abs/2308.10848	Simulation	Computation and Language (cs.CL)	agentverse_facilitating_multi-agent_collaboration_20230821	Tsinghua University, Beijing University of Posts and Telecommunications, Tencent Inc.
13	AI Hospital: Interactive Evaluation and Collaboration of LLMs as Intern Doctors for Clinical Diagnosis	Zhihao Fan, Jialong Tang, Wei Chen, Siyuan Wang, Zhongyu Wei, Jun Xi, Fei Huang, Jingren Zhou	2024.2.15	The incorporation of Large Language Models (LLMs) in healthcare marks a significant ad- vancement. However, the application has pre- dominantly been limited to discriminative and question-answering tasks, which does not fully leverage their interactive potential. To address this limitation, our paper presents AI Hospital, a framework designed to build a real-time in- teractive diagnosis environment. To simulate the procedure, we collect high-quality medical records to create patient, examiner, and medical director agents. AI Hospital is then utilized for the interactive evaluation and collaboration of LLMs. Initially, we create a Multi-View Medi- cal Evaluation (MVME) benchmark where vari- ous LLMs serve as intern doctors for interactive diagnosis. Subsequently, to improve diagnostic accuracy, we introduce a collaborative mech- anism that involves iterative discussions and a dispute resolution process under the supervi- sion of the medical director. In our experiments, we validate the reliability of AI Hospital. The results not only explore the feasibility of apply LLMs in clinical consultation but also confirm the effectiveness of the dispute resolution fo- cused collaboration method.	https://arxiv.org/abs/2402.09742	Simulation	Computation and Language (cs.CL)	ai_hospital_interactive_evaluation_20240215	Alibaba Inc., Huazhong University of Science and Technology, Fudan University
14	Apollo's Oracle: Retrieval-Augmented Reasoning in Multi-Agent Debates	Haotian Wang, Xiyuan Du, Weijiang Yu, Qianglong Chen, Kun Zhu, Zheng Chu, Lian Yan, Yi Guan	2023.12.8	Multi-agent debate systems are designed to derive accurate and consistent conclusions through adversarial interactions among agents. However, these systems often encounter challenges due to cognitive constraints, manifesting as (1) agents' obstinate adherence to incorrect viewpoints and (2) their propensity to abandon correct viewpoints. These issues are primarily responsible for the ineffectiveness of such debates. Addressing the challenge of cognitive constraints, we introduce a novel framework, the Multi-Agent Debate with Retrieval Augmented (MADRA). MADRA incorporates retrieval of prior knowledge into the debate process, effectively breaking cognitive constraints and enhancing the agents' reasoning capabilities. Furthermore, we have developed a self-selection module within this framework, enabling agents to autonomously select pertinent evidence, thereby minimizing the impact of irrelevant or noisy data. We have comprehensively tested and analyzed MADRA across six diverse datasets. The experimental results demonstrate that our approach significantly enhances performance across various tasks, proving the effectiveness of our proposed method.	https://arxiv.org/abs/2312.04854	Communication	Computation and Language (cs.CL)	apollo's_oracle_retrieval-augmented_reasoning_20231208	Harbin Institute of Technology, Sun Yat-sen University, Zhejiang University
15	Are you in a Masquerade? Exploring the Behavior and Impact of Large Language Model Driven Social Bots in Online Social Networks	Siyu Li, Jin Yang, Kui Zhao	2023.7.19	As the capabilities of Large Language Models (LLMs) emerge, they not only assist in accomplishing traditional tasks within more efficient paradigms but also stimulate the evolution of social bots. Researchers have begun exploring the implementation of LLMs as the driving core of social bots, enabling more efficient and user-friendly completion of tasks like profile completion, social behavior decision-making, and social content generation. However, there is currently a lack of systematic research on the behavioral characteristics of LLMs-driven social bots and their impact on social networks. We have curated data from Chirper, a Twitter-like social network populated by LLMs-driven social bots and embarked on an exploratory study. Our findings indicate that: (1) LLMs-driven social bots possess enhanced individual-level camouflage while exhibiting certain collective characteristics; (2) these bots have the ability to exert influence on online communities through toxic behaviors; (3) existing detection methods are applicable to the activity environment of LLMs-driven social bots but may be subject to certain limitations in effectiveness. Moreover, we have organized the data collected in our study into the Masquerade-23 dataset, which we have publicly released, thus addressing the data void in the subfield of LLMs-driven social bots behavior datasets. Our research outcomes provide primary insights for the research and governance of LLMs-driven social bots within the research community.	https://arxiv.org/abs/2307.10337	Simulation	Social and Information Networks (cs.SI)	are_you_in_a_20230719	Sichuan University
16	ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator	Junda Zhu, Lingyong Yan, Haibo Shi, Dawei Yin, Lei Sha	2024.5.28	Large language models (LLMs) are proven to benefit a lot from retrieval-augmented genera- tion (RAG) in alleviating hallucinations con- fronted with knowledge-intensive questions. RAG adopts information retrieval techniques to inject external knowledge from semantic- relevant documents as input contexts. How- ever, due to today’s Internet being flooded with numerous noisy and fabricating content, it is inevitable that RAG systems are vulnerable to these noises and prone to respond incor- rectly. To this end, we propose to optimize the retrieval-augmented GENERATOR with a Adversarial Tuning Multi-agent system (ATM). The ATM steers the GENERATOR to have a ro- bust perspective of useful documents for ques- tion answering with the help of an auxiliary ATTACKER agent. The GENERATOR and the ATTACKER are tuned adversarially for several iterations. After rounds of multi-agent itera- tive tuning, the GENERATOR can eventually better discriminate useful documents amongst fabrications. The experimental results verify the effectiveness of ATM and we also observe that the GENERATOR can achieve better perfor- mance compared to state-of-the-art baselines.	https://arxiv.org/abs/2405.18111	Communication	Computation and Language (cs.CL)	atm_adversarial_tuning_multi-agent_20240528	Beihang University, Baidu Inc.
17	Auto Arena of LLMs: Automating LLM Evaluations with Agent Peer-battles and Committee Discussions	Ruochen Zhao, Wenxuan Zhang, Yew Ken Chia, Deli Zhao, Lidong Bing	2024.5.30	As LLMs evolve on a daily basis, there is an urgent need for a trustworthy evaluation method that can provide robust evaluation results in a timely fashion. Currently, as static benchmarks are prone to contamination concerns, users tend to trust human voting platforms, such as Chatbot Arena. However, human annotations require extensive manual efforts. To provide an automatic, robust, and trustworthy evaluation framework, we innovatively propose the Auto-Arena of LLMs, which automates the entire evaluation process with LLM agents. Firstly, an examiner LLM devises queries. Then, a pair of candidate LLMs engage in a multi-round peer- battle around the query, during which the LLM’s true performance gaps become visible. Finally, a committee of LLM judges collectively discuss and determine the winner, which alleviates bias and promotes fairness. In our extensive experiment on the 17 newest LLMs, Auto-Arena shows the highest correlation with human preferences, providing a promising alternative to human evaluation platforms.	https://arxiv.org/abs/2405.20267	Communication	Computation and Language (cs.CL)	auto_arena_of_llms_20240530	Nanyang Technological University, Alibaba Group, Singapore University of Technology and Design
18	AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation	Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, Chi Wang	2023.8.16	AutoGen2 is an open-source framework that allows developers to build LLM ap- plications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in vari- ous modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic framework for building diverse applications of various complexities and LLM capacities. Em- pirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answer- ing, operations research, online decision-making, entertainment, etc.	https://arxiv.org/abs/2308.08155	Organization	Artificial Intelligence (cs.AI)	autogen_enabling_next-gen_llm_20230816	Microsoft Research, Pennsylvania State University, University of Washington, Xidian University
19	Autonomous Agents for Collaborative Task under Information Asymmetry	Wei Liu, Chenxi Wang, Yifei Wang, Zihao Xie, Rennai Qiu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Chen Qian	2024.6.21	Large Language Model Multi-Agent Systems (LLM-MAS) have achieved great progress in solving complex tasks. It performs communication among agents within the system to collaboratively solve tasks, under the premise of shared information. However, when agents’ communication is leveraged to enhance human cooperation, a new challenge arises due to information asymmetry, since each agent can only access the information of its human user. Previous MAS struggle to complete tasks under this condition. To address this, we propose a new MAS paradigm termed iAgents, which denotes Informative Multi-Agent Systems. In iAgents, the human social network is mirrored in the agent network, where agents proactively exchange human information necessary for task resolution, thereby overcoming information asymmetry. iAgents employs a novel agent reasoning mechanism, InfoNav, to navigate agents’ communication towards effective information exchange. Together with InfoNav, iAgents organizes human information in a mixed memory to provide agents with accurate and comprehensive information for exchange. Additionally, we introduce InformativeBench, the first benchmark tailored for evaluating LLM agents’ task-solving ability under information asymmetry. Experimental results show that iAgents can collaborate within a social network of 140 individuals and 588 relationships, autonomously communicate over 30 turns, and retrieve information from nearly 70,000 messages to complete tasks within 3 minutes.	https://arxiv.org/abs/2406.14928	Communication	Artificial Intelligence (cs.AI)	autonomous_agents_for_collaborative_20240621	Tsinghua University, Beijing University of Posts and Telecommunications
20	Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation	Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang	2023.10.2	Recent breakthroughs in large language models (LLMs) have brought remark- able success in the field of LLM-as-Agent. Nevertheless, a prevalent assumption is that the information processed by LLMs is consistently honest, neglecting the pervasive deceptive or misleading information in human society and AI-generated content. This oversight makes LLMs susceptible to malicious manipulations, potentially resulting in detrimental outcomes. This study utilizes the intricate Avalon game as a testbed to explore LLMs’ potential in deceptive environments. Avalon, full of misinformation and requiring sophisticated logic, manifests as a “Game-of-Thoughts”. Inspired by the efficacy of humans’ recursive thinking and perspective-taking in the Avalon game, we introduce a novel framework, Recur- sive Contemplation (ReCon), to enhance LLMs’ ability to identify and counteract deceptive information. ReCon combines formulation and refinement contempla- tion processes; formulation contemplation produces initial thoughts and speech, while refinement contemplation further polishes them. Additionally, we incor- porate first-order and second-order perspective transitions into these processes respectively. Specifically, the first-order allows an LLM agent to infer others’ mental states, and the second-order involves understanding how others perceive the agent’s mental state.......	https://arxiv.org/abs/2310.01320	Communication	Artificial Intelligence (cs.AI)	avalon's_game_of_thoughts_20231002	Tsinghua University, BIGAI, Technical University of Munich
21	Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation	Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang	2023.10.2	Recent breakthroughs in large language models (LLMs) have brought remark- able success in the field of LLM-as-Agent. Nevertheless, a prevalent assumption is that the information processed by LLMs is consistently honest, neglecting the pervasive deceptive or misleading information in human society and AI-generated content. This oversight makes LLMs susceptible to malicious manipulations, potentially resulting in detrimental outcomes. This study utilizes the intricate Avalon game as a testbed to explore LLMs’ potential in deceptive environments. Avalon, full of misinformation and requiring sophisticated logic, manifests as a “Game-of-Thoughts”. Inspired by the efficacy of humans’ recursive thinking and perspective-taking in the Avalon game, we introduce a novel framework, Recur- sive Contemplation (ReCon), to enhance LLMs’ ability to identify and counteract deceptive information. ReCon combines formulation and refinement contempla- tion processes; formulation contemplation produces initial thoughts and speech, while refinement contemplation further polishes them. Additionally, we incor- porate first-order and second-order perspective transitions into these processes respectively. Specifically, the first-order allows an LLM agent to infer others’ mental states, and the second-order involves understanding how others perceive the agent’s mental state.......	https://arxiv.org/abs/2310.01320	Organization	Artificial Intelligence (cs.AI)	avalon's_game_of_thoughts_20231002	Tsinghua University, BIGAI, Technical University of Munich
22	BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis	Shuhang Lin, Wenyue Hua, Lingyao Li, Che-Jui Chang, Lizhou Fan, Jianchao Ji, Hang Hua, Mingyu Jin, Jiebo Luo, Yongfeng Zhang	2024.4.23	This paper presents BattleAgent, a detailed emulation demonstration system that combines the Large Vision-Language Model (VLM) and Multi-Agent System (MAS). This novel system aims to simulate complex dynamic interactions among multiple agents, as well as between agents and their environments, over a period of time. It emulates both the decision-making processes of leaders and the viewpoints of ordinary participants, such as soldiers. The emulation showcases the current capabilities of agents, featuring fine-grained multi-modal interactions between agents and landscapes. It develops customizable agent structures to meet specific situational requirements, for example, a variety of battle-related activities like scouting and trench digging. These components collaborate to recreate historical events in a lively and comprehensive manner while offering insights into the thoughts and feelings of individuals from diverse viewpoints. The technological foundations of BattleAgent establish detailed and immersive settings for historical battles, enabling individual agents to partake in, observe, and dynamically respond to evolving battle scenarios. This methodology holds the potential to substantially deepen our understanding of historical events, particularly through individual accounts. Such initiatives can also aid historical research, as conventional historical narratives often lack documentation and prioritize the perspectives of decision- makers, thereby overlooking the experiences of ordinary individuals. This biased documentation results in a considerable gap in our historical understanding, as many stories remain untold......	https://arxiv.org/abs/2404.15532	Simulation	Human-Computer Interaction (cs.HC)	battleagent_multi-modal_dynamic_emulation_20240423	Rutgers University, University of Michigan, University of Rochester
23	Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication	Weize Chen, Chenfei Yuan, Jiarui Yuan, Yusheng Su, Chen Qian, Cheng Yang, Ruobing Xie, Zhiyuan Liu, Maosong Sun	2024.2.28	Natural language (NL) has long been the predominant format for human cognition and communication, and by extension, has been similarly pivotal in the development and application of Large Language Models (LLMs). Yet, besides NL, LLMs have seen various non-NL formats during pre-training, such as code and logical expression. NL's status as the optimal format for LLMs, particularly in single-LLM reasoning and multi-agent communication, has not been thoroughly examined. In this work, we challenge the default use of NL by exploring the utility of non-NL formats in these contexts. We show that allowing LLMs to autonomously select the most suitable format before reasoning or communicating leads to a 3.3 to 5.7\% improvement in reasoning efficiency for different LLMs, and up to a 72.7\% reduction in token usage in multi-agent communication, all while maintaining communicative effectiveness. Our comprehensive analysis further reveals that LLMs can devise a format from limited task instructions and that the devised format is effectively transferable across different LLMs. Intriguingly, the structured communication format decided by LLMs exhibits notable parallels with established agent communication languages, suggesting a natural evolution towards efficient, structured communication in agent communication.	https://arxiv.org/abs/2402.18439	Communication	Computation and Language (cs.CL)	beyond_natural_language_llms_20240228	Tsinghua University, Tencent, Beijing University of Posts and Telecommunications
24	Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication	Weize Chen, Chenfei Yuan, Jiarui Yuan, Yusheng Su, Chen Qian, Cheng Yang, Ruobing Xie, Zhiyuan Liu, Maosong Sun	2024.2.28	Natural language (NL) has long been the predominant format for human cognition and communication, and by extension, has been similarly pivotal in the development and application of Large Language Models (LLMs). Yet, besides NL, LLMs have seen various non-NL formats during pre-training, such as code and logical expression. NL's status as the optimal format for LLMs, particularly in single-LLM reasoning and multi-agent communication, has not been thoroughly examined. In this work, we challenge the default use of NL by exploring the utility of non-NL formats in these contexts. We show that allowing LLMs to autonomously select the most suitable format before reasoning or communicating leads to a 3.3 to 5.7\% improvement in reasoning efficiency for different LLMs, and up to a 72.7\% reduction in token usage in multi-agent communication, all while maintaining communicative effectiveness. Our comprehensive analysis further reveals that LLMs can devise a format from limited task instructions and that the devised format is effectively transferable across different LLMs. Intriguingly, the structured communication format decided by LLMs exhibits notable parallels with established agent communication languages, suggesting a natural evolution towards efficient, structured communication in agent communication.	https://arxiv.org/abs/2402.18439	Evolution	Computation and Language (cs.CL)	beyond_natural_language_llms_20240228	Tsinghua University, Tencent, Beijing University of Posts and Telecommunications
25	Building Cooperative Embodied Agents Modularly with Large Language Models	Hongxin Zhang, Weihua Du, Jiaming Shan, Qinhong Zhou, Yilun Du, Joshua B. Tenenbaum, Tianmin Shu, Chuang Gan	2023.7.5	In this work, we address challenging multi-agent cooperation problems with de- centralized control, raw sensory observations, costly communication, and multi- objective tasks instantiated in various embodied environments. While previous re- search either presupposes a cost-free communication channel or relies on a central- ized controller with shared observations, we harness the commonsense knowledge, reasoning ability, language comprehension, and text generation prowess of LLMs and seamlessly incorporate them into a cognitive-inspired modular framework that integrates with perception, memory, and execution. Thus building a Cooperative Embodied Language Agent CoELA, who can plan, communicate, and cooperate with others to accomplish long-horizon tasks efficiently. Our experiments on C- WAH and TDW-MAT demonstrate that CoELA driven by GPT-4 can surpass strong planning-based methods and exhibit emergent effective communication. Though current Open LMs like LLAMA-2 still underperform, we fine-tune a CoLLAMA with data collected with our agents and show how they can achieve promising performance. We also conducted a user study for human-agent interaction and discovered that CoELA communicating in natural language can earn more trust and cooperate more effectively with humans. Our research underscores the potential of LLMs for future research in multi-agent cooperation. Videos can be found on the project website https://vis-www.cs.umass.edu/Co-LLM-Agents/.	https://arxiv.org/abs/2307.02485	Communication	Artificial Intelligence (cs.AI)	building_cooperative_embodied_agents_20230705	University of Massachusetts Amherst, Tsinghua University, Shanghai Jiao Tong University, MIT, MIT-IBM Watson AI Lab
26	CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society	Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, Bernard Ghanem	2023.3.31	The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate au- tonomous cooperation among communicative agents, and provides insight into their “cognitive” processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role- playing . Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of a society of agents, providing a valuable resource for investigating conversational language models. In particular, we conduct com- prehensive studies on instruction-following cooperation in multi-agent settings. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabili- ties of multi-agent systems, and open-sourcing our library to support research on communicative agents and beyond: https://github.com/camel-ai/camel.	https://arxiv.org/abs/2303.17760	Communication	Artificial Intelligence (cs.AI)	camel_communicative_agents_for_20230331	King Abdullah University of Science and Technology
27	Can Large Language Model Agents Simulate Human Trust Behaviors?	Chengxing Xie, Canyu Chen, Feiran Jia, Ziyu Ye, Kai Shu, Adel Bibi, Ziniu Hu, Philip Torr, Bernard Ghanem, Guohao Li	2024.2.7	Large Language Model (LLM) agents have been increasingly adopted as simulation tools to model humans in applications such as social science. However, one fundamental question remains: can LLM agents really simulate human behaviors? In this paper, we focus on one of the most critical behaviors in human interactions, trust, and aim to investigate whether or not LLM agents can sim- ulate human trust behaviors. We first find that LLM agents generally exhibit trust behaviors, re- ferred to as agent trust, under the framework of Trust Games, which are widely recognized in be- havioral economics. Then, we discover that LLM agents can have high behavioral alignment with humans regarding trust behaviors, particularly for GPT-4, indicating the feasibility to simulate hu- man trust behaviors with LLM agents. In addition, we probe into the biases in agent trust and the differences in agent trust towards agents and hu- mans. We also explore the intrinsic properties of agent trust under conditions including advanced reasoning strategies and external manipulations. We further offer important implications of our discoveries for various scenarios where trust is paramount. Our study provides new insights into the behaviors of LLM agents and the fundamental analogy between LLMs and humans.	https://arxiv.org/abs/2402.04559	Simulation	Artificial Intelligence (cs.AI)	can_large_language_model_20240207	KAUST, Illinois Institute of Technology, Pennsylvania State University, The University of Chicago, University of Oxford, California Institute of Technology
28	Chain of Agents: Large Language Models Collaborating on Long-Context Tasks	Yusen Zhang, Ruoxi Sun, Yanfei Chen, Tomas Pfister, Rui Zhang, Sercan Ö. Arik	2024.6.4	Addressing the challenge of effectively processing long contexts has become a critical issue for Large Language Models (LLMs). Two common strategies have emerged: 1) reducing the input length, such as retrieving relevant chunks by Retrieval-Augmented Generation (RAG), and 2) expanding the context window limit of LLMs. However, both strategies have drawbacks: input reduction has no guarantee of covering the part with needed information, while window extension struggles with focusing on the pertinent information for solving the task. To mitigate these limitations, we propose Chain-of-Agents (CoA), a novel framework that harnesses multi-agent collaboration through natural language to enable information aggregation and context reasoning across various LLMs over long-context tasks. CoA consists of multiple worker agents who sequentially communicate to handle different segmented portions of the text, followed by a manager agent who synthesizes these contributions into a coherent final output. CoA processes the entire input by interleaving reading and reasoning, and it mitigates long context focus issues by assigning each agent a short context. We perform comprehensive evaluation of CoA on a wide range of long-context tasks in question answering, summarization, and code completion, demonstrating significant improvements by up to 10% over strong baselines of RAG, Full-Context, and multi-agent LLMs.	https://arxiv.org/abs/2406.02818	Organization	Computation and Language (cs.CL)	chain_of_agents_large_20240604	Penn State University, Google Cloud AI Research
29	ChatCoder: Chat-based Refine Requirement Improves LLMs' Code Generation	Zejun Wang, Jia Li, Ge Li, Zhi Jin	2023.11.1	Large language models have shown good performances in generat- ing code to meet human requirements. However, human require- ments expressed in natural languages can be vague, incomplete, and ambiguous, leading large language models to misunderstand human requirements and make mistakes. Worse, it is difficult for a human user to refine the requirement. To help human users refine their requirements and improve large language models’ code gen- eration performances, we propose ChatCoder: a method to refine the requirements via chatting with large language models. We de- sign a chat scheme in which the large language models will guide the human users to refine their expression of requirements to be more precise, unambiguous, and complete than before. Experiments show that ChatCoder has improved existing large language models’ performance by a large margin. Besides, ChatCoder has the advan- tage over refine-based methods and LLMs fine-tuned via human response.	https://arxiv.org/abs/2311.00272	Organization	Software Engineering (cs.SE)	chatcoder_chat-based_refine_requirement_20231101	Peking University
30	ChatDev: Communicative Agents for Software Development	Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, Maosong Sun	2023.7.16	Software development is a complex task that necessitates cooperation among multiple mem- bers with diverse skills. Numerous studies used deep learning to improve specific phases in a waterfall model, such as design, coding, and testing. However, the deep learning model in each phase requires unique designs, lead- ing to technical inconsistencies across various phases, which results in a fragmented and in- effective development process. In this paper, we introduce ChatDev, a chat-powered soft- ware development framework in which special- ized agents driven by large language models (LLMs) are guided in what to communicate (via chat chain) and how to communicate (via communicative dehallucination). These agents actively contribute to the design, coding, and testing phases through unified language-based communication, with solutions derived from their multi-turn dialogues. We found their uti- lization of natural language is advantageous for system design, and communicating in pro- gramming language proves helpful in debug- ging. This paradigm demonstrates how linguis- tic communication facilitates multi-agent col- laboration, establishing language as a unify- ing bridge for autonomous task-solving among LLM agents. The code and data are available at https://github.com/OpenBMB/ChatDev.	https://arxiv.org/abs/2307.07924	Communication	Software Engineering (cs.SE)	chatdev_communicative_agents_for_20230716	Tsinghua University, The University of Sydney, BUPT, Modelbest Inc.
31	ChatDev: Communicative Agents for Software Development	Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, Maosong Sun	2023.7.16	Software development is a complex task that necessitates cooperation among multiple mem- bers with diverse skills. Numerous studies used deep learning to improve specific phases in a waterfall model, such as design, coding, and testing. However, the deep learning model in each phase requires unique designs, lead- ing to technical inconsistencies across various phases, which results in a fragmented and in- effective development process. In this paper, we introduce ChatDev, a chat-powered soft- ware development framework in which special- ized agents driven by large language models (LLMs) are guided in what to communicate (via chat chain) and how to communicate (via communicative dehallucination). These agents actively contribute to the design, coding, and testing phases through unified language-based communication, with solutions derived from their multi-turn dialogues. We found their uti- lization of natural language is advantageous for system design, and communicating in pro- gramming language proves helpful in debug- ging. This paradigm demonstrates how linguis- tic communication facilitates multi-agent col- laboration, establishing language as a unify- ing bridge for autonomous task-solving among LLM agents. The code and data are available at https://github.com/OpenBMB/ChatDev.	https://arxiv.org/abs/2307.07924	Organization	Software Engineering (cs.SE)	chatdev_communicative_agents_for_20230716	Tsinghua University, The University of Sydney, BUPT, Modelbest Inc.
32	ChatDev: Communicative Agents for Software Development	Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, Maosong Sun	2023.7.16	Software development is a complex task that necessitates cooperation among multiple mem- bers with diverse skills. Numerous studies used deep learning to improve specific phases in a waterfall model, such as design, coding, and testing. However, the deep learning model in each phase requires unique designs, lead- ing to technical inconsistencies across various phases, which results in a fragmented and in- effective development process. In this paper, we introduce ChatDev, a chat-powered soft- ware development framework in which special- ized agents driven by large language models (LLMs) are guided in what to communicate (via chat chain) and how to communicate (via communicative dehallucination). These agents actively contribute to the design, coding, and testing phases through unified language-based communication, with solutions derived from their multi-turn dialogues. We found their uti- lization of natural language is advantageous for system design, and communicating in pro- gramming language proves helpful in debug- ging. This paradigm demonstrates how linguis- tic communication facilitates multi-agent col- laboration, establishing language as a unify- ing bridge for autonomous task-solving among LLM agents. The code and data are available at https://github.com/OpenBMB/ChatDev.	https://arxiv.org/abs/2307.07924	Simulation	Software Engineering (cs.SE)	chatdev_communicative_agents_for_20230716	Tsinghua University, The University of Sydney, BUPT, Modelbest Inc.
33	ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate	Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, Zhiyuan Liu	2023.8.14	Text evaluation has historically posed significant challenges, often demanding substantial labor and time cost. With the emergence of large language models (LLMs), researchers have explored LLMs’ potential as alternatives for human evaluation. While these single-agent-based approaches show promise, experi- mental results suggest that further advancements are needed to bridge the gap between their current effectiveness and human-level evaluation quality. Recog- nizing that best practices of human evaluation processes often involve multiple human annotators collaborating in the evaluation, we resort to a multi-agent debate framework, moving beyond single-agent prompting strategies. The multi-agent- based approach enables a group of LLMs to synergize with an array of intelli- gent counterparts, harnessing their distinct capabilities and expertise to enhance efficiency and effectiveness in handling intricate tasks. In this paper, we con- struct a multi-agent referee team called ChatEval to autonomously discuss and evaluate the quality of generated responses from different models on open-ended questions and traditional natural language generation (NLG) tasks. We derive insights and lessons from practical scenarios where humans instigate group dis- cussions for brainstorming and propose different communication strategies within ChatEval......	https://arxiv.org/abs/2308.07201	Organization	Computation and Language (cs.CL)	chateval_towards_better_llm-based_20230814	Tsinghua University, Hong Kong University of Science and Technology, Peking University
34	CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving	Pei Chen, Boran Han, Shuai Zhang	2024.4.26	Large Language Models (LLMs) have shown great ability in solving traditional natural lan- guage tasks and elementary reasoning tasks with appropriate prompting techniques. How- ever, their ability is still limited in solving com- plicated science problems. In this work, we aim to push the upper bound of the reason- ing capability of LLMs by proposing a col- laborative multi-agent, multi-reasoning-path (CoMM) prompting framework. Specifically, we prompt LLMs to play different roles in a problem-solving team, and encourage differ- ent role-play agents to collaboratively solve the target task. In particular, we discover that applying different reasoning paths for differ- ent roles is an effective strategy to implement few-shot prompting approaches in the multi- agent scenarios. Empirical results demonstrate the effectiveness of the proposed methods on two college-level science problems over com- petitive baselines. Our further analysis shows the necessity of prompting LLMs to play dif- ferent roles or experts independently. We re- lease the code at: https://github.com/ amazon-science/comm-prompt.	https://arxiv.org/abs/2404.17729	Organization	Computation and Language (cs.CL)	comm_collaborative_multi-agent,_multi-reasoning-path_20240426	Texas A&M University, Amazon Web Services
35	CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agents	Qinlin Zhao, Jindong Wang, Yixuan Zhang, Yiqiao Jin, Kaijie Zhu, Hao Chen, Xing Xie	2023.10.26	Large language models (LLMs) have been widely used as agents to complete different tasks, such as personal assistance or event planning. While most of the work has focused on cooperation and collaboration between agents, little work explores competition, another important mech- anism that promotes the development of soci- ety and economy. In this paper, we seek to ex- amine the competition dynamics in LLM-based agents. We first propose a general framework for studying the competition between agents. Then, we implement a practical competitive environ- ment using GPT-4 to simulate a virtual town with two types of agents, including restaurant agents and customer agents. Specifically, the restaurant agents compete with each other to attract more customers, where competition encourages them to transform, such as cultivating new operating strategies. Simulation experiments reveal several interesting findings at the micro and macro lev- els, which align well with existing market and sociological theories. We hope that the frame- work and environment can be a promising testbed to study the competition that fosters understand- ing of society. Code is available at: https: //github.com/microsoft/competeai.	https://arxiv.org/abs/2310.17512	Simulation	Artificial Intelligence (cs.AI)	competeai_understanding_the_competition_20231026	University of Science and Technology of China, Microsoft Research, William & Mary, Georgia Institute of Technology, Carnegie Mellon University
36	Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents	Zihao Wang, Shaofei Cai, Guanzhou Chen, Anji Liu, Xiaojian Ma, Yitao Liang	2023.2.3	We investigate the challenge of task planning for multi-task embodied agents in open-world environments. Two main difficulties are identified: 1) executing plans in an open-world environment (e.g., Minecraft) necessitates accurate and multi-step reasoning due to the long-term nature of tasks, and 2) as vanilla planners do not consider how easy the current agent can achieve a given sub-task when ordering parallel sub-goals within a complicated plan, the resulting plan could be inefficient or even infeasible. To this end, we propose "Describe, Explain, Plan and Select" (DEPS), an interactive planning approach based on Large Language Models (LLMs). DEPS facilitates better error correction on initial LLM-generated plan by integrating description of the plan execution process and providing self-explanation of feedback when encountering failures during the extended planning phases. Furthermore, it includes a goal selector, which is a trainable module that ranks parallel candidate sub-goals based on the estimated steps of completion, consequently refining the initial plan. Our experiments mark the milestone of the first zero-shot multi-task agent that can robustly accomplish 70+ Minecraft tasks and nearly double the overall performances. Further testing reveals our method's general effectiveness in popularly adopted non-open-ended domains as well (i.e., ALFWorld and tabletop manipulation). The ablation and exploratory studies detail how our design beats the counterparts and provide a promising update on the 𝙾𝚋𝚝𝚊𝚒𝚗𝙳𝚒𝚊𝚖𝚘𝚗𝚍 grand challenge with our approach.	https://arxiv.org/abs/2302.01560	Organization	Artificial Intelligence (cs.AI)	describe,_explain,_plan_and_20230203	Peking University, University of California Los Angeles, Beijing Institute for General Artificial Intelligence
37	Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization	Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, Diyi Yang	2023.10.3	Large language model (LLM) agents have been shown effective on a wide range of tasks, and by ensembling multiple LLM agents, their performances could be further improved. Existing approaches employ a fixed set of agents to interact with each other in a static architecture, which limits their generalizability to vari- ous tasks and requires strong human prior in designing these agents. In this work, we propose to construct a strategic team of agents communicating in a dynamic interaction architecture based on the task query. Specifically, we build a frame- work named Dynamic LLM-Agent Network (DyLAN) for LLM-agent collabora- tion on complicated tasks like reasoning and code generation. DyLAN enables agents to interact for multiple rounds in a dynamic architecture with inference- time agent selection and an early-stopping mechanism to improve performance and efficiency. We further design an automatic agent team optimization algorithm based on an unsupervised metric termed Agent Importance Score, enabling the selection of best agents based on the contribution each agent makes. Empirically, we demonstrate that DyLAN performs well in both reasoning and code generation tasks with reasonable computational cost. DyLAN achieves 1	https://arxiv.org/abs/2310.02170	Organization	Computation and Language (cs.CL)	dynamic_llm-agent_network_an_20231003	Tsinghua University, Georgia Tech, Stanford University
38	Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization	Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, Diyi Yang	2023.10.3	Large language model (LLM) agents have been shown effective on a wide range of tasks, and by ensembling multiple LLM agents, their performances could be further improved. Existing approaches employ a fixed set of agents to interact with each other in a static architecture, which limits their generalizability to vari- ous tasks and requires strong human prior in designing these agents. In this work, we propose to construct a strategic team of agents communicating in a dynamic interaction architecture based on the task query. Specifically, we build a frame- work named Dynamic LLM-Agent Network (DyLAN) for LLM-agent collabora- tion on complicated tasks like reasoning and code generation. DyLAN enables agents to interact for multiple rounds in a dynamic architecture with inference- time agent selection and an early-stopping mechanism to improve performance and efficiency. We further design an automatic agent team optimization algorithm based on an unsupervised metric termed Agent Importance Score, enabling the selection of best agents based on the contribution each agent makes. Empirically, we demonstrate that DyLAN performs well in both reasoning and code generation tasks with reasonable computational cost. DyLAN achieves 1	https://arxiv.org/abs/2310.02170	Evolution	Computation and Language (cs.CL)	dynamic_llm-agent_network_an_20231003	Tsinghua University, Georgia Tech, Stanford University
39	EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities	Nian Li, Chen Gao, Mingyu Li, Yong Li, Qingmin Liao	2023.10.16	The advent of artificial intelligence has led to a growing emphasis on data-driven modeling in macroeconomics, with agent-based modeling (ABM) emerging as a prominent bottom-up simulation paradigm. In ABM, agents (e.g., households, firms) interact within a macroe- conomic environment, collectively generating market dynamics. Existing agent modeling typ- ically employs predetermined rules or learning- based neural networks for decision-making. However, customizing each agent presents sig- nificant challenges, complicating the modeling of agent heterogeneity. Additionally, the in- fluence of multi-period market dynamics and multifaceted macroeconomic factors are often overlooked in decision-making processes. In this work, we introduce EconAgent, a large language model-empowered agent with human- like characteristics for macroeconomic simu- lation. We first construct a simulation envi- ronment that incorporates various market dy- namics driven by agents’ decisions regarding work and consumption. Through the perception module, we create heterogeneous agents with distinct decision-making mechanisms. Fur- thermore, we model the impact of macroeco- nomic trends using a memory module, which allows agents to reflect on past individual ex- periences and market dynamics. Simulation experiments show that EconAgent can make realistic decisions, leading to more reasonable macroeconomic phenomena compared to exist- ing rule-based or learning-based agents. Our codes are released at https://github.com/ tsinghua-fib-lab/ACL24-EconAgent.	https://arxiv.org/abs/2310.10436	Organization	Artificial Intelligence (cs.AI)	econagent_large_language_model-empowered_20231016	Tsinghua University
40	EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities	Nian Li, Chen Gao, Mingyu Li, Yong Li, Qingmin Liao	2023.10.16	The advent of artificial intelligence has led to a growing emphasis on data-driven modeling in macroeconomics, with agent-based modeling (ABM) emerging as a prominent bottom-up simulation paradigm. In ABM, agents (e.g., households, firms) interact within a macroe- conomic environment, collectively generating market dynamics. Existing agent modeling typ- ically employs predetermined rules or learning- based neural networks for decision-making. However, customizing each agent presents sig- nificant challenges, complicating the modeling of agent heterogeneity. Additionally, the in- fluence of multi-period market dynamics and multifaceted macroeconomic factors are often overlooked in decision-making processes. In this work, we introduce EconAgent, a large language model-empowered agent with human- like characteristics for macroeconomic simu- lation. We first construct a simulation envi- ronment that incorporates various market dy- namics driven by agents’ decisions regarding work and consumption. Through the perception module, we create heterogeneous agents with distinct decision-making mechanisms. Fur- thermore, we model the impact of macroeco- nomic trends using a memory module, which allows agents to reflect on past individual ex- periences and market dynamics. Simulation experiments show that EconAgent can make realistic decisions, leading to more reasonable macroeconomic phenomena compared to exist- ing rule-based or learning-based agents. Our codes are released at https://github.com/ tsinghua-fib-lab/ACL24-EconAgent.	https://arxiv.org/abs/2310.10436	Simulation	Artificial Intelligence (cs.AI)	econagent_large_language_model-empowered_20231016	Tsinghua University
41	Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate	Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Zhaopeng Tu, Shuming Shi	2023.5.30	Modern large language models (LLMs) like ChatGPT have shown remarkable performance on general language tasks but still struggle on complex reasoning tasks, which drives the re- search on cognitive behaviors of LLMs to ex- plore human-like problem-solving strategies. Along this direction, one representative strat- egy is self-reflection, which asks an LLM to refine the solution with the feedback gener- ated by itself iteratively. However, our study shows that such reflection-style methods suf- fer from the Degeneration-of-Thought (DoT) problem: once the LLM has established confi- dence in its solutions, it is unable to generate novel thoughts later through reflection even if its initial stance is incorrect. To address the DoT problem, we propose a Multi-Agent De- bate (MAD) framework, in which multiple agents express their arguments in the state of “tit for tat” and a judge manages the debate process to obtain a final solution. Clearly, our MAD framework encourages divergent think- ing in LLMs which would be helpful for tasks that require deep levels of contemplation. Ex- periment results on two challenging datasets, commonsense machine translation and counter- intuitive arithmetic reasoning, demonstrate the effectiveness of our MAD framework. Exten- sive analyses suggest that the adaptive break of debate and the modest level of “tit for tat” state are required for MAD to obtain good perfor- mance. Moreover, we find that LLMs might not be a fair judge if different LLMs are used for agents. Code is available at https://github. com/Skytliang/Multi-Agents-Debate.	https://arxiv.org/abs/2305.19118	Communication	Computation and Language (cs.CL)	encouraging_divergent_thinking_in_20230530	Tsinghua University, Shanghai Jiao Tong University, Tencent AI Lab
42	Epidemic Modeling with Generative Agents	Ross Williams, Niyousha Hosseinichimeh, Aritra Majumdar, Navid Ghaffarzadegan	2023.7.11	This study offers a new paradigm of individual-level modeling to address the grand challenge of incorporating human behavior in epidemic models. Using generative artificial intelligence in an agent-based epidemic model, each agent is empowered to make its own reasonings and decisions via connecting to a large language model such as ChatGPT. Through various simulation experiments, we present compelling evidence that generative agents mimic real-world behaviors such as quarantining when sick and self-isolation when cases rise. Collectively, the agents demonstrate patterns akin to multiple waves observed in recent pandemics followed by an endemic period. Moreover, the agents successfully flatten the epidemic curve. This study creates potential to improve dynamic system modeling by offering a way to represent human brain, reasoning, and decision making.	https://arxiv.org/abs/2307.04986	Simulation	Artificial Intelligence (cs.AI)	epidemic_modeling_with_generative_20230711	Virginia Tech
43	Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate	Kai Xiong, Xiao Ding, Yixin Cao, Ting Liu, Bing Qin	2023.5.19	Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face various inconsistency issues. Existing works primarily focus on the incon- sistency issues within a single LLM, while we complementarily explore the inter-consistency among multiple LLMs for collaboration. To examine whether LLMs can collaborate effec- tively to achieve a consensus for a shared goal, we focus on commonsense reasoning, and in- troduce a formal debate framework (FORD) to conduct a three-stage debate among LLMs with real-world scenarios alignment: fair de- bate, mismatched debate, and roundtable de- bate. Through extensive experiments on var- ious datasets, LLMs can effectively collabo- rate to reach a consensus despite noticeable inter-inconsistencies, but imbalances in their abilities can lead to domination by superior LLMs. Leveraging a more advanced LLM like GPT-4 as an authoritative judge can boost col- laboration performance. Our work contributes to understanding the inter-consistency among LLMs and lays the foundation for develop- ing future collaboration methods. Codes and data are available at https://github.com/Waste- Wood/FORD.	https://arxiv.org/abs/2305.11595	Communication	Computation and Language (cs.CL)	examining_inter-consistency_of_large_20230519	Harbin Institute of Technology, Singapore Management University
44	Experiential Co-Learning of Software-Developing Agents	Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, Yifei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun	2023.12.28	Recent advancements in large language mod- els (LLMs) have brought significant changes to various domains, especially through LLM- driven autonomous agents. A representative scenario is in software development, where LLM agents demonstrate efficient collabora- tion, task division, and assurance of software quality, markedly reducing the need for man- ual involvement. However, these agents fre- quently perform a variety of tasks indepen- dently, without benefiting from past experi- ences, which leads to repeated mistakes and inefficient attempts in multi-step task execu- tion. To this end, we introduce Experiential Co- Learning, a novel LLM-agent learning frame- work in which instructor and assistant agents gather shortcut-oriented experiences from their historical trajectories and use these past expe- riences for future task execution. The exten- sive experiments demonstrate that the frame- work enables agents to tackle unseen software- developing tasks more effectively. We antici- pate that our insights will guide LLM agents towards enhanced autonomy and contribute to their evolutionary growth in cooperative learning. The code and data are available at https://github.com/OpenBMB/ChatDev.	https://arxiv.org/abs/2312.17025	Evolution	Computation and Language (cs.CL)	experiential_co-learning_of_software-developing_20231228	Tsinghua University, Dalian University of Technology, Beijing University of Posts and Telecommunications, Siemens
45	Experiential Co-Learning of Software-Developing Agents	Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, Yifei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun	2023.12.28	Recent advancements in large language mod- els (LLMs) have brought significant changes to various domains, especially through LLM- driven autonomous agents. A representative scenario is in software development, where LLM agents demonstrate efficient collabora- tion, task division, and assurance of software quality, markedly reducing the need for man- ual involvement. However, these agents fre- quently perform a variety of tasks indepen- dently, without benefiting from past experi- ences, which leads to repeated mistakes and inefficient attempts in multi-step task execu- tion. To this end, we introduce Experiential Co- Learning, a novel LLM-agent learning frame- work in which instructor and assistant agents gather shortcut-oriented experiences from their historical trajectories and use these past expe- riences for future task execution. The exten- sive experiments demonstrate that the frame- work enables agents to tackle unseen software- developing tasks more effectively. We antici- pate that our insights will guide LLM agents towards enhanced autonomy and contribute to their evolutionary growth in cooperative learning. The code and data are available at https://github.com/OpenBMB/ChatDev.	https://arxiv.org/abs/2312.17025	Organization	Computation and Language (cs.CL)	experiential_co-learning_of_software-developing_20231228	Tsinghua University, Dalian University of Technology, Beijing University of Posts and Telecommunications, Siemens
46	Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View	Jintian Zhang, Xin Xu, Ningyu Zhang, Ruibo Liu, Bryan Hooi, Shumin Deng	2023.10.3	As Natural Language Processing (NLP) sys- tems are increasingly employed in intricate so- cial environments, a pressing query emerges: Can these NLP systems mirror human-esque collaborative intelligence, in a multi-agent so- ciety consisting of multiple large language mod- els (LLMs)? This paper probes the collabora- tion mechanisms among contemporary NLP systems by melding practical experiments with theoretical insights. We fabricate four unique ‘societies’ comprised of LLM agents, where each agent is characterized by a specific ‘trait’ (easy-going or overconfident) and engages in collaboration with a distinct ‘thinking pattern’ (debate or reflection). Through evaluating these multi-agent societies on three benchmark datasets, we discern that certain collaborative strategies not only outshine previous top-tier approaches but also optimize efficiency (using fewer API tokens). Moreover, our results fur- ther illustrate that LLM agents manifest human- like social behaviors, such as conformity and consensus reaching, mirroring foundational so- cial psychology theories. In conclusion, we integrate insights from social psychology to contextualize the collaboration of LLM agents, inspiring further investigations into the collab- oration mechanism for LLMs. We have shared our code and datasets1, hoping to catalyze fur- ther research in this promising avenue.	https://arxiv.org/abs/2310.02124	Simulation	Computation and Language (cs.CL)	exploring_collaboration_mechanisms_for_20231003	Zhejiang University, National University of Singapore, NUS-NCS Joint Lab, Google DeepMind
47	Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf	Yuzhuang Xu, Shuo Wang, Peng Li, Fuwen Luo, Xiaolong Wang, Weidong Liu, Yang Liu	2023.9.9	Communication games, which we refer to as incomplete information games that heavily de- pend on natural language communication, hold significant research value in fields such as eco- nomics, social science, and artificial intelli- gence. In this work, we explore the problem of how to engage large language models (LLMs) in communication games, and in response, pro- pose a tuning-free framework. Our approach keeps LLMs frozen, and relies on the retrieval and reflection on past communications and ex- periences for improvement. An empirical study on the representative and widely-studied com- munication game, “Werewolf”, demonstrates that our framework can effectively play Were- wolf game without tuning the parameters of the LLMs. More importantly, strategic behaviors begin to emerge in our experiments, suggest- ing that it will be a fruitful journey to engage LLMs in communication games and associated domains.	https://arxiv.org/abs/2309.04658	Communication	Computation and Language (cs.CL)	exploring_large_language_models_20230909	Tsinghua University, Zhongguancun Laboratory
48	Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf	Yuzhuang Xu, Shuo Wang, Peng Li, Fuwen Luo, Xiaolong Wang, Weidong Liu, Yang Liu	2023.9.9	Communication games, which we refer to as incomplete information games that heavily de- pend on natural language communication, hold significant research value in fields such as eco- nomics, social science, and artificial intelli- gence. In this work, we explore the problem of how to engage large language models (LLMs) in communication games, and in response, pro- pose a tuning-free framework. Our approach keeps LLMs frozen, and relies on the retrieval and reflection on past communications and ex- periences for improvement. An empirical study on the representative and widely-studied com- munication game, “Werewolf”, demonstrates that our framework can effectively play Were- wolf game without tuning the parameters of the LLMs. More importantly, strategic behaviors begin to emerge in our experiments, suggest- ing that it will be a fruitful journey to engage LLMs in communication games and associated domains.	https://arxiv.org/abs/2309.04658	Organization	Computation and Language (cs.CL)	exploring_large_language_models_20230909	Tsinghua University, Zhongguancun Laboratory
49	Facilitating Multi-Role and Multi-Behavior Collaboration of Large Language Models for Online Job Seeking and Recruiting	Hongda Sun, Hongzhan Lin, Haiyu Yan, Chen Zhu, Yang Song, Xin Gao, Shuo Shang, Rui Yan	2024.5.28	The emergence of online recruitment services has revolutionized the traditional landscape of job seeking and recruitment, neces- sitating the development of high-quality industrial applications to improve person-job fitting. Existing methods generally rely on modeling the latent semantics of resumes and job descriptions and learning a matching function between them. Inspired by the pow- erful role-playing capabilities of Large Language Models (LLMs), we propose to introduce a mock interview process between LLM- played interviewers and candidates. The mock interview conver- sations can provide additional evidence for candidate evaluation, thereby augmenting traditional person-job fitting based solely on resumes and job descriptions. However, characterizing these two roles in online recruitment still presents several challenges, such as developing the skills to raise interview questions, formulating appropriate answers, and evaluating two-sided fitness. To this end, we propose MockLLM, a novel applicable framework that divides the person-job matching process into two modules: mock interview generation and two-sided evaluation in handshake protocol, jointly enhancing their performance through collaborative behaviors between interviewers and candidates. We design a role- playing framework as a multi-role and multi-behavior paradigm to enable a single LLM agent to effectively behave with multiple functions for both parties......	https://arxiv.org/abs/2405.18113	Organization	Computation and Language (cs.CL)	facilitating_multi-role_and_multi-behavior_20240528	Renmin University of China, BOSS Zhipin, King Abdullah University of Science and Technology, University of Electronic Science and Technology of China
50	GameGPT: Multi-agent Collaborative Framework for Game Development	Dake Chen, Hanbin Wang, Yunhao Huo, Yuzhao Li, Haoyang Zhang	2023.10.12	The large language model (LLM) based agents have demonstrated their capacity to automate and expedite software development processes. In this paper, we focus on game development and propose a multi-agent collaborative framework, dubbed GameGPT, to automate game development. While many studies have pinpointed hallucination as a primary roadblock for deploying LLMs in production, we identify another concern: redundancy. Our framework presents a series of methods to mitigate both concerns. These methods include dual collaboration and layered approaches with several in-house lexicons, to mitigate the hallucination and redundancy in the planning, task identification, and implementation phases. Furthermore, a decoupling approach is also introduced to achieve code generation with better precision.	https://arxiv.org/abs/2310.08067	Organization	Artificial Intelligence (cs.AI)	gamegpt_multi-agent_collaborative_framework_20231012	AutoGame Research, X-Institute, University of Southern California
51	Generative Agents: Interactive Simulacra of Human Behavior	Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein	2023.4.7	Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extends a large language model to store a complete record of the agent's experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty five agents using natural language. In an evaluation, these generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time. We demonstrate through ablation that the components of our agent architecture--observation, planning, and reflection--each contribute critically to the believability of agent behavior. By fusing large language models with computational, interactive agents, this work introduces architectural and interaction patterns for enabling believable simulations of human behavior.	https://arxiv.org/abs/2304.03442	Communication	Human-Computer Interaction (cs.HC)	generative_agents_interactive_simulacra_20230407	Stanford University, Google Research, Google DeepMind
52	Generative Agents: Interactive Simulacra of Human Behavior	Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein	2023.4.7	Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extends a large language model to store a complete record of the agent's experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty five agents using natural language. In an evaluation, these generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time. We demonstrate through ablation that the components of our agent architecture--observation, planning, and reflection--each contribute critically to the believability of agent behavior. By fusing large language models with computational, interactive agents, this work introduces architectural and interaction patterns for enabling believable simulations of human behavior.	https://arxiv.org/abs/2304.03442	Organization	Human-Computer Interaction (cs.HC)	generative_agents_interactive_simulacra_20230407	Stanford University, Google Research, Google DeepMind
53	Generative Agents: Interactive Simulacra of Human Behavior	Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein	2023.4.7	Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extends a large language model to store a complete record of the agent's experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty five agents using natural language. In an evaluation, these generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time. We demonstrate through ablation that the components of our agent architecture--observation, planning, and reflection--each contribute critically to the believability of agent behavior. By fusing large language models with computational, interactive agents, this work introduces architectural and interaction patterns for enabling believable simulations of human behavior.	https://arxiv.org/abs/2304.03442	Simulation	Human-Computer Interaction (cs.HC)	generative_agents_interactive_simulacra_20230407	Stanford University, Google Research, Google DeepMind
54	Humanoid Agents: Platform for Simulating Human-like Generative Agents	Zhilin Wang, Yu Ying Chiu, Yu Cheung Chiu	2023.10.9	Just as computational simulations of atoms, molecules and cells have shaped the way we study the sciences, true-to-life simulations of human-like agents can be valuable tools for studying human behavior. We propose Humanoid Agents, a system that guides Generative Agents to behave more like humans by introducing three elements of System 1 processing: Basic needs (e.g. hunger, health and energy), Emotion and Closeness in Relationships. Humanoid Agents are able to use these dynamic elements to adapt their daily activities and conversations with other agents, as supported with empirical experiments. Our system is designed to be extensible to various settings, three of which we demonstrate, as well as to other elements influencing human behavior (e.g. empathy, moral values and cultural background). Our platform also includes a Unity WebGL game interface for visualization and an interactive analytics dashboard to show agent statuses over time.	https://arxiv.org/abs/2310.05418	Simulation	Computation and Language (cs.CL)	humanoid_agents_platform_for_20231009	University of Washington, NVIDIA, The University of Hong Kong
55	Improving Factuality and Reasoning in Language Models through Multiagent Debate	Yilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, Igor Mordatch	2023.5.23	Large language models (LLMs) have demonstrated remarkable capabilities in language generation, understanding, and few-shot learning in recent years. An extensive body of work has explored how their performance may be further im- proved through the tools of prompting, ranging from verification, self-consistency, or intermediate scratchpads. In this paper, we present a complementary approach to improve language responses where multiple language model instances propose and debate their individual responses and reasoning processes over multiple rounds to arrive at a common final answer. Our findings indicate that this approach significantly enhances mathematical and strategic reasoning across a number of tasks. We also demonstrate that our approach improves the factual validity of generated content, reducing fallacious answers and hallucinations that contem- porary models are prone to. Our approach may be directly applied to existing black-box models and uses identical procedure and prompts for all tasks we inves- tigate. Overall, our findings suggest that such "society of minds" approach has the potential to significantly advance the capabilities of LLMs and pave the way for further breakthroughs in language generation and understanding. Project website at https://composable-models.github.io/llm_debate/.	https://arxiv.org/abs/2305.14325	Communication	Computation and Language (cs.CL)	improving_factuality_and_reasoning_20230523	MIT CSAIL, Google Brain
56	Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback	Yao Fu, Hao Peng, Tushar Khot, Mirella Lapata	2023.5.17	We study whether multiple large language models (LLMs) can autonomously improve each other in a negotiation game by playing, reflecting, and criticizing. We are interested in this question because if LLMs were able to improve each other, it would imply the possibility of creating strong AI agents with minimal human intervention. We ask two LLMs to negotiate with each other, playing the roles of a buyer and a seller, respectively. They aim to reach a deal with the buyer targeting a lower price and the seller a higher one. A third language model, playing the critic, provides feedback to a player to improve the player’s negotiation strategies. We let the two agents play multiple rounds, using previous negotiation history and AI feedback as in-context demonstrations to improve the model’s negotiation strategy iteratively. We use different LLMs (GPT and Claude) for different roles and use the deal price as the evaluation metric. Our experiments reveal multiple intriguing findings: (	https://arxiv.org/abs/2305.10142	Communication	Computation and Language (cs.CL)	improving_language_model_negotiation_20230517	University of Edinburgh, Allen Institute for AI, University of Edinburgh
57	Improving Multi-Agent Debate with Sparse Communication Topology	Yunxuan Li, Yibing Du, Jiageng Zhang, Le Hou, Peter Grabowski, Yeqing Li, Eugene Ie	2024.6.17	Multi-agent debate has proven effective in im- proving large language models quality for rea- soning and factuality tasks. While various role- playing strategies in multi-agent debates have been explored, in terms of the communica- tion among agents, existing approaches adopt a brute force algorithm – each agent can com- municate with all other agents. In this paper, we systematically investigate the effect of com- munication connectivity in multi-agent systems. Our experiments on GPT and Mistral models re- veal that multi-agent debates leveraging sparse communication topology can achieve compara- ble or superior performance while significantly reducing computational costs. Furthermore, we extend the multi-agent debate framework to multimodal reasoning and alignment labeling tasks, showcasing its broad applicability and effectiveness. Our findings underscore the im- portance of communication connectivity on en- hancing the efficiency and effectiveness of the “society of minds” approach.	https://arxiv.org/abs/2406.11776	Organization	Computation and Language (cs.CL)	improving_multi-agent_debate_with_20240617	Google, Google DeepMind
58	Improving Multi-Agent Debate with Sparse Communication Topology	Yunxuan Li, Yibing Du, Jiageng Zhang, Le Hou, Peter Grabowski, Yeqing Li, Eugene Ie	2024.6.17	Multi-agent debate has proven effective in im- proving large language models quality for rea- soning and factuality tasks. While various role- playing strategies in multi-agent debates have been explored, in terms of the communica- tion among agents, existing approaches adopt a brute force algorithm – each agent can com- municate with all other agents. In this paper, we systematically investigate the effect of com- munication connectivity in multi-agent systems. Our experiments on GPT and Mistral models re- veal that multi-agent debates leveraging sparse communication topology can achieve compara- ble or superior performance while significantly reducing computational costs. Furthermore, we extend the multi-agent debate framework to multimodal reasoning and alignment labeling tasks, showcasing its broad applicability and effectiveness. Our findings underscore the im- portance of communication connectivity on en- hancing the efficiency and effectiveness of the “society of minds” approach.	https://arxiv.org/abs/2406.11776	Communication	Computation and Language (cs.CL)	improving_multi-agent_debate_with_20240617	Google, Google DeepMind
59	Iterative Experience Refinement of Software-Developing Agents	Chen Qian, Jiahao Li, Yufan Dang, Wei Liu, YiFei Wang, Zihao Xie, Weize Chen, Cheng Yang, Yingli Zhang, Zhiyuan Liu, Maosong Sun	2024.5.7	Autonomous agents powered by large language models (LLMs) show significant potential for achieving high autonomy in various scenar- ios such as software development. Recent re- search has shown that LLM agents can lever- age past experiences to reduce errors and en- hance efficiency. However, the static experi- ence paradigm, reliant on a fixed collection of past experiences acquired heuristically, lacks iterative refinement and thus hampers agents’ adaptability. In this paper, we introduce the It- erative Experience Refinement framework, en- abling LLM agents to refine experiences itera- tively during task execution. We propose two fundamental patterns: the successive pattern, refining based on nearest experiences within a task batch, and the cumulative pattern, acquir- ing experiences across all previous task batches. Augmented with our heuristic experience elim- ination, the method prioritizes high-quality and frequently-used experiences, effectively man- aging the experience space and enhancing effi- ciency. Extensive experiments show that while the successive pattern may yield superior re- sults, the cumulative pattern provides more sta- ble performance......	https://arxiv.org/abs/2405.04219	Evolution	Computation and Language (cs.CL)	iterative_experience_refinement_of_20240507	Tsinghua University, Dalian University of Technology, Beijing University of Posts and Telecommunications, Siemens
60	Iterative Experience Refinement of Software-Developing Agents	Chen Qian, Jiahao Li, Yufan Dang, Wei Liu, YiFei Wang, Zihao Xie, Weize Chen, Cheng Yang, Yingli Zhang, Zhiyuan Liu, Maosong Sun	2024.5.7	Autonomous agents powered by large language models (LLMs) show significant potential for achieving high autonomy in various scenar- ios such as software development. Recent re- search has shown that LLM agents can lever- age past experiences to reduce errors and en- hance efficiency. However, the static experi- ence paradigm, reliant on a fixed collection of past experiences acquired heuristically, lacks iterative refinement and thus hampers agents’ adaptability. In this paper, we introduce the It- erative Experience Refinement framework, en- abling LLM agents to refine experiences itera- tively during task execution. We propose two fundamental patterns: the successive pattern, refining based on nearest experiences within a task batch, and the cumulative pattern, acquir- ing experiences across all previous task batches. Augmented with our heuristic experience elim- ination, the method prioritizes high-quality and frequently-used experiences, effectively man- aging the experience space and enhancing effi- ciency. Extensive experiments show that while the successive pattern may yield superior re- sults, the cumulative pattern provides more sta- ble performance......	https://arxiv.org/abs/2405.04219	Organization	Computation and Language (cs.CL)	iterative_experience_refinement_of_20240507	Tsinghua University, Dalian University of Technology, Beijing University of Posts and Telecommunications, Siemens
61	Language Agents as Digital Representatives in Collective Decision-Making	Jarrett, Daniel and Pislar, Miruna and Bakker, Michiel A and Tessler, Michael Henry and Koster, Raphael and Balaguer, Jan and Elie, Romuald and Summerfield, Christopher and Tacchetti, Andrea	2023.11.8	Consider the process of collective decision-making, in which a group of individuals interactively select a preferred outcome from among a universe of alternatives. In this context, “representation” is the activity of making an individual’s preferences present in the process via participation by a proxy agent—i.e. their “representative”. To this end, learned models of human behavior have the potential to fill this role, with practical implications for multi-agent scenario studies and mechanism design. In this work, we investigate the possibility of training language agents to behave in the capacity of representatives of human agents, appropriately expressing the preferences of those individuals whom they stand for. First, we formalize the setting of collective decision-making—as the episodic process of interaction between a group of agents and a decision mechanism. On this basis, we then formalize the problem of digital representation—as the simulation of an agent’s behavior to yield equivalent outcomes from the mechanism. Finally, we conduct an empirical case study in the setting of consensus-finding among diverse humans, and demonstrate the feasibility of fine-tuning large language models to act as digital representatives.	https://openreview.net/pdf?id=sv7KZcUqu1	Simulation		language_agents_as_digital_20231108	Google DeepMind
62	Language Agents as Optimizable Graphs	Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, Jürgen Schmidhuber	2024.2.26	Various human-designed prompt engineering techniques have been proposed to improve problem solvers based on Large Language Models (LLMs), yielding many disparate code bases. We unify these approaches by describing LLM-based agents as computational graphs. The nodes implement functions to process multimodal data or query LLMs, and the edges describe the information flow between operations. Graphs can be recursively combined into larger composite graphs representing hierarchies of inter-agent collaboration (where edges connect operations of different agents). Our novel automatic graph optimizers (1) refine node-level LLM prompts (node optimization) and (2) improve agent orchestration by changing graph connectivity (edge optimization). Experiments demonstrate that our framework can be used to efficiently develop, integrate, and automatically improve various LLM agents.	https://arxiv.org/abs/2402.16823	Organization	Artificial Intelligence (cs.AI)	language_agents_as_optimizable_20240226	King Abdullah University of Science and Technology, The Swiss AI Lab IDSIA, USI, SUPSI
63	Language Agents as Optimizable Graphs	Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, Jürgen Schmidhuber	2024.2.26	Various human-designed prompt engineering techniques have been proposed to improve problem solvers based on Large Language Models (LLMs), yielding many disparate code bases. We unify these approaches by describing LLM-based agents as computational graphs. The nodes implement functions to process multimodal data or query LLMs, and the edges describe the information flow between operations. Graphs can be recursively combined into larger composite graphs representing hierarchies of inter-agent collaboration (where edges connect operations of different agents). Our novel automatic graph optimizers (1) refine node-level LLM prompts (node optimization) and (2) improve agent orchestration by changing graph connectivity (edge optimization). Experiments demonstrate that our framework can be used to efficiently develop, integrate, and automatically improve various LLM agents.	https://arxiv.org/abs/2402.16823	Evolution	Artificial Intelligence (cs.AI)	language_agents_as_optimizable_20240226	King Abdullah University of Science and Technology, The Swiss AI Lab IDSIA, USI, SUPSI
64	Large Language Models are Diverse Role-Players for Summarization Evaluation	Ning Wu, Ming Gong, Linjun Shou, Shining Liang, Daxin Jiang	2023.3.27	. Text summarization has a wide range of applications in many scenarios. The evaluation of the quality of the generated text is a complex problem. A big challenge to language evaluation is that there is a clear divergence between existing metrics and human evaluation. A document summary’s quality can be assessed by human annotators on various criteria, both objective ones like grammar and correctness, and subjective ones like informativeness, succinctness, and appeal. Most of the automatic evaluation methods like BLUE/ROUGE may be not able to adequately capture the above dimensions. In this paper, we propose a new evaluation framework based on LLMs, which provides a comprehensive evaluation framework by comparing generated text and reference text from both objective and subjective aspects. First, we propose to model objective and subjective dimensions of generated text based on roleplayers prompting mechanism. Furthermore, we introduce a context-based prompting mechanism that is able to generate dynamic roleplayer profiles based on input context. Finally, we design a multi-roleplayer prompting technology based on batch prompting and integrate multiple outputs into the final evaluation results. Experimental results on three real datasets for summarization show that our model is highly competitive and has a very high consistency with human annotators.	https://arxiv.org/abs/2303.15078	Organization	Computation and Language (cs.CL)	large_language_models_are_20230327	Microsoft
65	Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game	Qianqiao Xu, Zhiliang Tian, Hongyan Wu, Zhen Huang, Yiping Song, Feng Liu, Dongsheng Li	2024.4.3	With the enhanced performance of large models on natural language processing tasks, potential moral and ethical issues of large models arise. There exist ma- licious attackers who induce large models to jailbreak and generate information containing illegal, privacy-invasive information through techniques such as prompt engineering. As a result, large models counter malicious attackers’ attacks using techniques such as safety alignment. However, the strong defense mechanism of the large model through rejection replies is easily identified by attackers and used to strengthen attackers’ capabilities. In this paper, we propose a multi-agent attacker-disguiser game approach to achieve a weak defense mechanism that allows the large model to both safely reply to the attacker and hide the defense intent. First, we construct a multi-agent framework to simulate attack and defense scenarios, playing different roles to be responsible for attack, disguise, safety evaluation, and disguise evaluation tasks. After that, we design attack and disguise game algorithms to optimize the game strategies of the attacker and the disguiser and use the curriculum learning process to strengthen the capabilities of the agents. The experiments verify that the method in this paper is more effective in strengthening the model’s ability to disguise the defense intent compared with other methods. Moreover, our approach can adapt any black-box large model to assist the model in defense and does not suffer from model version iterations.	https://arxiv.org/abs/2404.02532	Organization	Artificial Intelligence (cs.AI)	learn_to_disguise_avoid_20240403	National University of Defense Technology, Guangdong University of Foreign Studies,
66	Leveraging Large Language Models for Collective Decision-Making	Marios Papachristou, Longqi Yang, Chin-Chia Hsu	2023.11.3	In various work contexts, such as meeting scheduling, collaborating, and project planning, collective decision-making is essential but often challenging due to diverse individual preferences, varying work focuses, and power dynamics among members. To address this, we propose a system leveraging Large Language Models (LLMs) to facilitate group decision-making by managing conversations and balancing preferences among individuals. Our system aims to extract individual preferences from conversations and suggest options that satisfy the preferences of the members. We specifically apply this system to corporate meeting scheduling. We create synthetic employee profiles and simulate conversations at scale, leveraging LLMs to evaluate the system performance as a novel approach to conducting a user study. Our results indicate efficient coordination with reduced interactions between the members and the LLM-based system. The system refines and improves its proposed options over time, ensuring that many of the members' individual preferences are satisfied in an equitable way. Finally, we conduct a survey study involving human participants to assess our system's ability to aggregate preferences and reasoning about them. Our findings show that the system exhibits strong performance in both dimensions	https://arxiv.org/abs/2311.04928	Organization	Computation and Language (cs.CL)	leveraging_large_language_models_20231103	Cornell University, Microsoft
67	LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay	Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang	2023.10.23	This paper explores the open research prob- lem of understanding the social behaviors of LLM-based agents. Using Avalon as a testbed, we employ system prompts to guide LLM agents in gameplay. While previous studies have touched on gameplay with LLM agents, research on their social behaviors is lacking. We propose a novel framework, tailored for Avalon, features a multi-agent system facil- itating efficient communication and interac- tion. We evaluate its performance based on game success and analyze LLM agents’ so- cial behaviors. Results affirm the framework’s effectiveness in creating adaptive agents and suggest LLM-based agents’ potential in nav- igating dynamic social interactions. By ex- amining collaboration and confrontation be- haviors, we offer insights into this field’s re- search and applications. Our code is pub- licly available at https://github.com/ 3DAgentWorld/LLM-Game-Agent	https://arxiv.org/abs/2310.14985	Communication	Computation and Language (cs.CL)	llm-based_agent_society_investigation_20231023	The Hong Kong University of Science and Technology (Guangzhou), Singapore University of Technology and Design, Singapore Management University, Verily Life Sciences, Tencent
68	LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay	Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang	2023.10.23	This paper explores the open research prob- lem of understanding the social behaviors of LLM-based agents. Using Avalon as a testbed, we employ system prompts to guide LLM agents in gameplay. While previous studies have touched on gameplay with LLM agents, research on their social behaviors is lacking. We propose a novel framework, tailored for Avalon, features a multi-agent system facil- itating efficient communication and interac- tion. We evaluate its performance based on game success and analyze LLM agents’ so- cial behaviors. Results affirm the framework’s effectiveness in creating adaptive agents and suggest LLM-based agents’ potential in nav- igating dynamic social interactions. By ex- amining collaboration and confrontation be- haviors, we offer insights into this field’s re- search and applications. Our code is pub- licly available at https://github.com/ 3DAgentWorld/LLM-Game-Agent	https://arxiv.org/abs/2310.14985	Organization	Computation and Language (cs.CL)	llm-based_agent_society_investigation_20231023	The Hong Kong University of Science and Technology (Guangzhou), Singapore University of Technology and Design, Singapore Management University, Verily Life Sciences, Tencent
69	LLM-Driven Agents for Influencer Selection in Digital Advertising Campaigns	Xiaoqing Zhang, Xiuying Chen, Yuhan Liu, Jianzhou Wang, Zhenxing Hu, Rui Yan	2024.3.22	In the digital world, influencers are pivotal as opinion leaders, shap- ing the views and choices of their influencees. Modern advertising often follows this trend, where marketers choose appropriate in- fluencers for product endorsements, based on thorough market analysis. Previous studies on influencer selection have typically relied on numerical representations of individual opinions and interactions, a method that simplifies the intricacies of social dy- namics. With the development of large language models (LLMs), we now have the opportunity to capture the nuanced exchanges of information within social networks. Hence, in this work, we first introduce an Influencer Dynamics Simulator (IDS), helping promoters identify and select the right influencers to market their products, based on LLM simulation. Concretely, we first propose an influencer-influencee engagement-based pre-selection module to screen potential influencer candidates. Subsequently, a simulation is constructed for these candidates and their influencees. Each user is represented as an LLM-based agent, drawing from their interaction history to deduce their profile and interests. The influencee agents will predict their behavior in response to influencer advertising. Fi- nally, we develop a ranking metric designed to pinpoint influencers who are most likely to drive product purchases based on feedback from their influencees. To evaluate our framework, we collect a real-world advertising network dataset, including social relations, post and comment content, and user behaviors.......	https://arxiv.org/abs/2403.15105	Simulation	Social and Information Networks (cs.SI)	llm-driven_agents_for_influencer_20240322	Renmin University of China, King Abdullah University of Science and Technology, Moonshot AI
70	LM vs LM: Detecting Factual Errors via Cross Examination	Roi Cohen, May Hamri, Mor Geva, Amir Globerson	2023.5.22	A prominent weakness of modern language models (LMs) is their tendency to generate fac- tually incorrect text, which hinders their us- ability. A natural question is whether such fac- tual errors can be detected automatically. In- spired by truth-seeking mechanisms in law, we propose a factuality evaluation framework for LMs that is based on cross-examination. Our key idea is that an incorrect claim is likely to result in inconsistency with other claims that the model generates. To discover such incon- sistencies, we facilitate a multi-turn interaction between the LM that generated the claim and another LM (acting as an examiner) which in- troduces questions to discover inconsistencies. We empirically evaluate our method on factual claims made by multiple recent LMs on four benchmarks, finding that it outperforms exist- ing methods and baselines, often by a large gap. Our results demonstrate the potential of using interacting LMs to capture factual errors.	https://arxiv.org/abs/2305.13281	Communication	Computation and Language (cs.CL)	lm_vs_lm_detecting_20230522	Tel Aviv University, Google DeepMind, Google Research
71	LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration	Jun Zhao, Can Zu, Hao Xu, Yi Lu, Wei He, Yiwen Ding, Tao Gui, Qi Zhang, Xuanjing Huang	2024.2.18	Large language models (LLMs) have demon- strated impressive performance in understand- ing language and executing complex reasoning tasks. However, LLMs with long context win- dows have been notorious for their expensive training costs and high inference latency. Even the most advanced models such as GPT-4 and Claude2 often make mistakes when processing inputs of over 100k tokens, a phenomenon also known as lost in the middle. In this paper, we propose LONGAGENT, a method based on multi-agent collaboration, which scales LLMs (e.g., LLaMA) to a context of 128K and demonstrates potential superiority in long-text processing compared to GPT-	https://arxiv.org/abs/2402.11550	Organization	Computation and Language (cs.CL)	longagent_scaling_language_models_20240218	Fudan University
72	Lyfe Agents: Generative agents for low-cost real-time social interactions	Zhao Kaiya, Michelangelo Naim, Jovana Kondic, Manuel Cortes, Jiaxin Ge, Shuying Luo, Guangyu Robert Yang, Andrew Ahn	2023.10.3	Highly autonomous generative agents powered by large language models promise to simulate intricate social behaviors in virtual societies. However, achieving real-time interactions with humans at a low computational cost remains challenging. Here, we introduce Lyfe Agents. They combine low-cost with real-time responsiveness, all while remaining intelligent and goal-oriented. Key innovations include: (1) an option-action framework, reducing the cost of high-level decisions; (2) asynchronous self-monitoring for better self-consistency; and (3) a Summarize-and-Forget memory mechanism, prioritizing critical memory items at a low cost. We evaluate Lyfe Agents' self-motivation and sociability across several multi-agent scenarios in our custom LyfeGame 3D virtual environment platform. When equipped with our brain-inspired techniques, Lyfe Agents can exhibit human-like self-motivated social reasoning. For example, the agents can solve a crime (a murder mystery) through autonomous collaboration and information exchange. Meanwhile, our techniques enabled Lyfe Agents to operate at a computational cost 10-100 times lower than existing alternatives. Our findings underscore the transformative potential of autonomous generative agents to enrich human social experiences in virtual worlds.	https://arxiv.org/abs/2310.02172	Evolution	Human-Computer Interaction (cs.HC)	lyfe_agents_generative_agents_20231003	Massachusetts Institute of Technology, Peking University, LyfeAL
73	Lyfe Agents: Generative agents for low-cost real-time social interactions	Zhao Kaiya, Michelangelo Naim, Jovana Kondic, Manuel Cortes, Jiaxin Ge, Shuying Luo, Guangyu Robert Yang, Andrew Ahn	2023.10.3	Highly autonomous generative agents powered by large language models promise to simulate intricate social behaviors in virtual societies. However, achieving real-time interactions with humans at a low computational cost remains challenging. Here, we introduce Lyfe Agents. They combine low-cost with real-time responsiveness, all while remaining intelligent and goal-oriented. Key innovations include: (1) an option-action framework, reducing the cost of high-level decisions; (2) asynchronous self-monitoring for better self-consistency; and (3) a Summarize-and-Forget memory mechanism, prioritizing critical memory items at a low cost. We evaluate Lyfe Agents' self-motivation and sociability across several multi-agent scenarios in our custom LyfeGame 3D virtual environment platform. When equipped with our brain-inspired techniques, Lyfe Agents can exhibit human-like self-motivated social reasoning. For example, the agents can solve a crime (a murder mystery) through autonomous collaboration and information exchange. Meanwhile, our techniques enabled Lyfe Agents to operate at a computational cost 10-100 times lower than existing alternatives. Our findings underscore the transformative potential of autonomous generative agents to enrich human social experiences in virtual worlds.	https://arxiv.org/abs/2310.02172	Simulation	Human-Computer Interaction (cs.HC)	lyfe_agents_generative_agents_20231003	Massachusetts Institute of Technology, Peking University, LyfeAL
74	MetaAgents: Simulating Interactions of Human Behaviors for LLM-based Task-oriented Coordination via Collaborative Generative Agents	Yuan Li, Yixuan Zhang, Lichao Sun	2023.10.10	Significant advancements have occurred in the application of Large Language Models (LLMs) for various tasks and social simulations. Despite this, their capac- ities to coordinate within task-oriented social contexts are under-explored. Such capabilities are crucial if LLMs are to effectively mimic human-like social be- havior and produce meaningful results. To bridge this gap, we introduce collab- orative generative agents, endowing LLM-based Agents with consistent behavior patterns and task-solving abilities. We situate these agents in a simulated job fair environment as a case study to scrutinize their coordination skills. We propose a novel framework that equips collaborative generative agents with human-like reasoning abilities and specialized skills. Our evaluation demonstrates that these agents show promising performance. However, we also uncover limitations that hinder their effectiveness in more complex coordination tasks. Our work provides valuable insights into the role and evolution of LLMs in task-oriented social sim- ulations.	https://arxiv.org/abs/2310.06500	Organization	Artificial Intelligence (cs.AI)	metaagents_simulating_interactions_of_20231010	University of Cambridge, William & Mary, Lehigh University
75	MetaAgents: Simulating Interactions of Human Behaviors for LLM-based Task-oriented Coordination via Collaborative Generative Agents	Yuan Li, Yixuan Zhang, Lichao Sun	2023.10.10	Significant advancements have occurred in the application of Large Language Models (LLMs) for various tasks and social simulations. Despite this, their capac- ities to coordinate within task-oriented social contexts are under-explored. Such capabilities are crucial if LLMs are to effectively mimic human-like social be- havior and produce meaningful results. To bridge this gap, we introduce collab- orative generative agents, endowing LLM-based Agents with consistent behavior patterns and task-solving abilities. We situate these agents in a simulated job fair environment as a case study to scrutinize their coordination skills. We propose a novel framework that equips collaborative generative agents with human-like reasoning abilities and specialized skills. Our evaluation demonstrates that these agents show promising performance. However, we also uncover limitations that hinder their effectiveness in more complex coordination tasks. Our work provides valuable insights into the role and evolution of LLMs in task-oriented social sim- ulations.	https://arxiv.org/abs/2310.06500	Simulation	Artificial Intelligence (cs.AI)	metaagents_simulating_interactions_of_20231010	University of Cambridge, William & Mary, Lehigh University
76	MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework	Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, Jürgen Schmidhuber	2023.8.1	Remarkable progress has been made on automated problem solving through so- cieties of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT en- codes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On col- laborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-based multi-agent systems. Our project can be found at https://github.com/geekan/MetaGPT	https://arxiv.org/abs/2308.00352	Organization	Artificial Intelligence (cs.AI)	metagpt_meta_programming_for_20230801	DeepWisdom, King Abdullah University of Science and Technology, Xiamen University, The Chinese University of Hong Kong (Shenzhen), Nanjing University, University of Pennsylvania University of California, Berkeley, The Swiss AI Lab IDSIA/USI/SUPSI
77	Mora: Enabling Generalist Video Generation via A Multi-Agent Framework	Zhengqing Yuan, Ruoxi Chen, Zhaoxu Li, Haolong Jia, Lifang He, Chi Wang, Lichao Sun	2024.3.20	Sora is the first large-scale generalist video generation model that garnered significant attention across society. Since its launch by OpenAI in February 2024, no other video generation models have paralleled {Sora}'s performance or its capacity to support a broad spectrum of video generation tasks. Additionally, there are only a few fully published video generation models, with the majority being closed-source. To address this gap, this paper proposes a new multi-agent framework Mora, which incorporates several advanced visual AI agents to replicate generalist video generation demonstrated by Sora. In particular, Mora can utilize multiple visual agents and successfully mimic Sora's video generation capabilities in various tasks, such as (1) text-to-video generation, (2) text-conditional image-to-video generation, (3) extend generated videos, (4) video-to-video editing, (5) connect videos and (6) simulate digital worlds. Our extensive experimental results show that Mora achieves performance that is proximate to that of Sora in various tasks. However, there exists an obvious performance gap between our work and Sora when assessed holistically. In summary, we hope this project can guide the future trajectory of video generation through collaborative AI agents.	https://arxiv.org/abs/2403.13248	Organization	Computer Vision and Pattern Recognition (cs.CV)	mora_enabling_generalist_video_20240320	Lehigh University, Microsoft Research
78	Multi-Agent Software Development through Cross-Team Collaboration	Zhuoyun Du, Chen Qian, Wei Liu, Zihao Xie, Yifei Wang, Yufan Dang, Weize Chen, Cheng Yang	2024.6.13	The latest breakthroughs in Large Language Models (LLMs), e.g., ChatDev, have catalyzed profound transformations, particularly through multi-agent collaboration for software devel- opment. LLM agents can collaborate in teams like humans, and follow the waterfall model to sequentially work on requirements analysis, development, review, testing, and other phases to perform autonomous software generation. However, for an agent team, each phase in a single development process yields only one pos- sible outcome. This results in the completion of only one development chain, thereby losing the opportunity to explore multiple potential decision paths within the solution space. Con- sequently, this may lead to obtaining subop- timal results. To address this challenge, we introduce Cross-Team Collaboration (CTC), a scalable multi-team framework that enables orchestrated teams to jointly propose various decisions and communicate with their insights in a cross-team collaboration environment for superior content generation. Experimental re- sults in software development reveal a notable increase in quality compared to state-of-the- art baselines, underscoring the efficacy of our framework. The significant improvements in story generation demonstrate the promising generalization ability of our framework across various domains. We anticipate that our work will guide LLM agents towards a cross-team paradigm and contribute to their significant growth in but not limited to software devel- opment. The code and data will be available at https://github.com/OpenBMB/ChatDev.	https://arxiv.org/abs/2406.08979	Organization	Computation and Language (cs.CL)	multi-agent_software_development_through_20240613	Zhejiang University, Tsinghua University, Beijing University of Posts and Telecommunications
79	MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate	Alfonso Amayuelas, Xianjun Yang, Antonis Antoniades, Wenyue Hua, Liangming Pan, William Wang	2024.6.20	Large Language Models (LLMs) have shown exceptional results on current benchmarks when working individually. The advancement in their capabilities, along with a reduction in parameter size and inference times, has facil- itated the use of these models as agents, en- abling interactions among multiple models to execute complex tasks. Such collaborations offer several advantages, including the use of specialized models (e.g. coding), improved confidence through multiple computations, and enhanced divergent thinking, leading to more diverse outputs. Thus, the collaborative use of language models is expected to grow signifi- cantly in the coming years. In this work, we evaluate the behavior of a network of models collaborating through debate under the influ- ence of an adversary. We introduce pertinent metrics to assess the adversary’s effectiveness, focusing on system accuracy and model agree- ment. Our findings highlight the importance of a model’s persuasive ability in influencing others. Additionally, we explore inference-time methods to generate more compelling argu- ments and evaluate the potential of prompt- based mitigation as a defensive strategy.	https://arxiv.org/abs/2406.14711v1	Organization	Computation and Language (cs.CL)	multiagent_collaboration_attack_investigating_20240620	UC Santa Barbara, Rutgers University
80	On Generative Agents in Recommendation	An Zhang, Yuxin Chen, Leheng Sheng, Xiang Wang, Tat-Seng Chua	2023.10.16	Recommender systems are the cornerstone of today's information dissemination, yet a disconnect between offline metrics and online performance greatly hinders their development. Addressing this challenge, we envision a recommendation simulator, capitalizing on recent breakthroughs in human-level intelligence exhibited by Large Language Models (LLMs). We propose Agent4Rec, a user simulator in recommendation, leveraging LLM-empowered generative agents equipped with user profile, memory, and actions modules specifically tailored for the recommender system. In particular, these agents' profile modules are initialized using real-world datasets (e.g. MovieLens, Steam, Amazon-Book), capturing users' unique tastes and social traits; memory modules log both factual and emotional memories and are integrated with an emotion-driven reflection mechanism; action modules support a wide variety of behaviors, spanning both taste-driven and emotion-driven actions. Each agent interacts with personalized recommender models in a page-by-page manner, relying on a pre-implemented collaborative filtering-based recommendation algorithm. We delve into both the capabilities and limitations of Agent4Rec, aiming to explore an essential research question: ``To what extent can LLM-empowered generative agents faithfully simulate the behavior of real, autonomous humans in recommender systems?'' Extensive and multi-faceted evaluations of Agent4Rec highlight both the alignment and deviation between agents and user-personalized preferences. Beyond mere performance comparison, we explore insightful experiments, such as emulating the filter bubble effect and discovering the underlying causal relationships in recommendation tasks.	https://arxiv.org/abs/2310.10108	Simulation	Information Retrieval (cs.IR)	on_generative_agents_in_20231016	National University of Singapore, Tsinghua University, University of Science and Technology of China
81	Out of One, Many: Using Language Models to Simulate Human Samples	Lisa P. Argyle, Ethan C. Busby, Nancy Fulda, Joshua Gubler, Christopher Rytting, David Wingate	2022.9.14	We propose and explore the possibility that language models can be studied as effective proxies for specific human sub-populations in social science research. Practical and research applications of artificial intelligence tools have sometimes been limited by problematic biases (such as racism or sexism), which are often treated as uniform properties of the models. We show that the "algorithmic bias" within one such tool -- the GPT-3 language model -- is instead both fine-grained and demographically correlated, meaning that proper conditioning will cause it to accurately emulate response distributions from a wide variety of human subgroups. We term this property "algorithmic fidelity" and explore its extent in GPT-3. We create "silicon samples" by conditioning the model on thousands of socio-demographic backstories from real human participants in multiple large surveys conducted in the United States. We then compare the silicon and human samples to demonstrate that the information contained in GPT-3 goes far beyond surface similarity. It is nuanced, multifaceted, and reflects the complex interplay between ideas, attitudes, and socio-cultural context that characterize human attitudes. We suggest that language models with sufficient algorithmic fidelity thus constitute a novel and powerful tool to advance understanding of humans and society across a variety of disciplines.	https://arxiv.org/abs/2209.06899	Simulation	Machine Learning (cs.LG)	out_of_one_many_20220914	Brigham Young University
82	PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games	Qinglin Zhu, Runcong Zhao, Jinhua Du, Lin Gui, Yulan He	2024.4.26	We propose PLAYER*, a novel framework that addresses the limitations of existing agent-based approaches built on Large Language Models (LLMs) in handling complex questions and understanding interpersonal relationships in dynamic environments. PLAYER* enhances path planning in Murder Mystery Games (MMGs) using an anytime sampling-based planner and a questioning-driven search framework. By equipping agents with a set of sensors, PLAYER* eliminates the need for pre-defined questions and enables agents to navigate complex social interactions. We additionally make a contribution by introducing a quantifiable evaluation method using multiple-choice questions and present WellPlay, a dataset containing 1,482 question-answer pairs. Experimental results demonstrate PLAYER*'s superiority over existing multi-agent methods, enhancing the generalisability and adaptability of agents in MMGs and paving the way for more effective multi-agent interactions.	https://arxiv.org/abs/2404.17662	Communication	Computation and Language (cs.CL)	player_enhancing_llm-based_multi-agent_20240426	King’s College London, Huawei London Research Centre, The Alan Turing Institute
83	Quantifying the Impact of Large Language Models on Collective Opinion Dynamics	Chao Li, Xing Su, Haoying Han, Cong Xue, Chunmo Zheng, Chao Fan	2023.8.7	The process of opinion expression and exchange is a critical component of democratic societies. As people interact with large language models (LLMs) in the opinion shaping process different from traditional media, the impacts of LLMs are increasingly recognized and being concerned. However, the knowledge about how LLMs affect the process of opinion expression and exchange of social opinion networks is very limited. Here, we create an opinion network dynamics model to encode the opinions of LLMs, cognitive acceptability and usage strategies of individuals, and simulate the impact of LLMs on opinion dynamics in a variety of scenarios. The outcomes of the simulations inform about effective demand-oriented opinion network interventions. The results from this study suggested that the output opinion of LLMs has a unique and positive effect on the collective opinion difference. The marginal effect of cognitive acceptability on collective opinion formation is nonlinear and shows a decreasing trend. When people partially rely on LLMs, the exchange process of opinion becomes more intense and the diversity of opinion becomes more favorable. In fact, there is 38.6% more opinion diversity when people all partially rely on LLMs, compared to prohibiting the use of LLMs entirely. The optimal diversity of opinion was found when the fractions of people who do not use, partially rely on, and fully rely on LLMs reached roughly 4:12:1. Our experiments also find that introducing extra agents with opposite/neutral/random opinions, we can effectively mitigate the impact of biased/toxic output from LLMs. Our findings provide valuable insights into opinion dynamics in the age of LLMs, highlighting the need for customized interventions tailored to specific scenarios to address the drawbacks of improper output and use of LLMs.	https://arxiv.org/abs/2308.03313	Simulation	Social and Information Networks (cs.SI)	quantifying_the_impact_of_20230807	Zhejiang University, Clemson University,
84	ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs	Justin Chih-Yao Chen, Swarnadeep Saha, Mohit Bansal	2023.9.22	Large Language Models (LLMs) still struggle with natural language reasoning tasks. Motivated by the society of minds (Minsky, 1988), we propose ReConcile, a multi-model multi-agent framework designed as a round table conference among diverse LLM agents. ReConcile enhances collaborative reasoning between LLM agents via multiple rounds of discussion, learning to convince other agents to improve their answers, and employing a confidence-weighted voting mechanism that leads to a better consensus. In each round, ReConcile initiates discussion between agents via a 'discussion prompt' that consists of (a) grouped answers and explanations generated by each agent in the previous round, (b) their confidence scores, and (c) demonstrations of answer-rectifying human explanations, used for convincing other agents. Experiments on seven benchmarks demonstrate that ReConcile significantly improves LLMs' reasoning -- both individually and as a team -- surpassing prior single-agent and multi-agent baselines by up to 11.4% and even outperforming GPT-4 on three datasets. ReConcile also flexibly incorporates different combinations of agents, including API-based, open-source, and domain-specific models, leading to an 8% improvement on MATH. Finally, we analyze the individual components of ReConcile, demonstrating that the diversity originating from different models is critical to its superior performance.	https://arxiv.org/abs/2309.13007	Organization	Computation and Language (cs.CL)	reconcile_round-table_conference_improves_20230922	UNC Chapel Hill
85	Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?	Qineng Wang, Zihao Wang, Ying Su, Hanghang Tong, Yangqiu Song	2024.2.28	Recent progress in LLMs discussion suggests that multi-agent discussion improves the rea- soning abilities of LLMs. In this work, we reevaluate this claim through systematic experi- ments, where we propose a novel group discus- sion framework to enrich the set of discussion mechanisms. Interestingly, our results show that a single-agent LLM with strong prompts can achieve almost the same performance as the best existing discussion approach on a wide range of reasoning tasks and backbone LLMs. We observe that the multi-agent discussion per- forms better than a single agent only when there is no demonstration in the prompt. Further study reveals the common interaction mecha- nisms of LLMs during the discussion.	https://arxiv.org/abs/2402.18272	Organization	Computation and Language (cs.CL)	rethinking_the_bounds_of_20240228	Zhejiang University, HKUST, UIUC
86	RoCo: Dialectic Multi-Robot Collaboration with Large Language Models	Zhao Mandi, Shreeya Jain, Shuran Song	2023.7.10	: We propose a novel approach to multi-robot collaboration that har- nesses the power of pre-trained large language models (LLMs) for both high-level communication and low-level path planning. Robots are equipped with LLMs to discuss and collectively reason task strategies. They then generate sub-task plans and task space waypoint paths, which are used by a multi-arm motion planner to accelerate trajectory planning. We also provide feedback from the environment, such as collision checking, and prompt the LLM agents to improve their plan and waypoints in-context. For evaluation, we introduce RoCoBench, a 6-task bench- mark covering a wide range of multi-robot collaboration scenarios, accompanied by a text-only dataset for agent representation and reasoning. We experimentally demonstrate the effectiveness of our approach – it achieves high success rates across all tasks in RoCoBench and adapts to variations in task semantics. Our di- alog setup offers high interpretability and flexibility – in real world experiments, we show RoCo easily incorporates human-in-the-loop, where a user can commu- nicate and collaborate with a robot agent to complete tasks together. See project website project-roco.github.io for videos and code.	https://arxiv.org/abs/2307.04738	Communication	Robotics (cs.RO)	roco_dialectic_multi-robot_collaboration_20230710	Columbia University
87	S3: Social-network Simulation System with Large Language Model-Empowered Agents	Chen Gao, Xiaochong Lan, Zhihong Lu, Jinzhu Mao, Jinghua Piao, Huandong Wang, Depeng Jin, Yong Li	2023.7.27	Simulation plays a crucial role in addressing various challenges within social science. It offers extensive applications such as state prediction, phenomena ex- planation, and policy-making support, among others. In this work, we harness the human-like capabilities of large language models (LLMs) in sensing, reasoning, and behaving, and utilize these qualities to construct the S3 system (short for Social network Simulation System). Adhering to the widely employed agent-based simulation paradigm, we employ fine-tuning and prompt engineering techniques to ensure that the agent’s behavior closely emulates that of a genuine human within the social network. Specifically, we simulate three pivotal aspects: emotion, at- titude, and interaction behaviors. By endowing the agent in the system with the ability to perceive the informational environment and emulate human actions, we observe the emergence of population-level phenomena, including the propagation of information, attitudes, and emotions. We conduct an evaluation encompassing two levels of simulation, employing real-world social network data. Encouragingly, the results demonstrate promising accuracy. This work represents an initial step in the realm of social network simulation empowered by LLM-based agents. We an- ticipate that our endeavors will serve as a source of inspiration for the development of simulation systems within, but not limited to, social science.	https://arxiv.org/abs/2307.14984	Simulation	Social and Information Networks (cs.SI)	s3_social-network_simulation_system_20230727	Tsinghua University
88	Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?	Yongchao Chen, Jacob Arkin, Yang Zhang, Nicholas Roy, Chuchu Fan	2023.9.27	— A flurry of recent work has demonstrated that pre-trained large language models (LLMs) can be effective task planners for a variety of single-robot tasks. The planning performance of LLMs is significantly improved via prompting techniques, such as in-context learning or re-prompting with state feedback, placing new importance on the token budget for the context window. An under-explored but natural next direction is to investigate LLMs as multi-robot task planners. However, long-horizon, heterogeneous multi-robot planning introduces new challenges of coordination while also pushing up against the limits of context window length. It is therefore critical to find token-efficient LLM planning frameworks that are also able to reason about the complexities of multi-robot coordination. In this work, we compare the task success rate and token efficiency of four multi-agent communication frameworks (centralized, decentralized, and two hybrid) as applied to four coordination-dependent multi-agent 2D task scenarios for increasing numbers of agents. We find that a hybrid framework achieves better task success rates across all four tasks and scales better to more agents. We further demonstrate the hybrid frameworks in 3D simulations where the vision-to-text problem and dynamical errors are considered.	https://arxiv.org/abs/2309.15943	Organization	Robotics (cs.RO)	scalable_multi-robot_collaboration_with_20230927	Massachusetts Institute of Technology, Harvard University, MIT-IBM Watson AI Lab.
89	Scaling Large-Language-Model-based Multi-Agent Collaboration	Chen Qian, Zihao Xie, Yifei Wang, Wei Liu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, Maosong Sun	2024.6.11	Pioneering advancements in large language model-powered agents have underscored the design pattern of multi-agent collaboration, demonstrating that collective intelligence can surpass the capabilities of each individual. In- spired by the neural scaling law, which posits that increasing neurons leads to emergent abil- ities, this study investigates whether a simi- lar principle applies to increasing agents in multi-agent collaboration. Technically, we propose ::multi-agent :collaboration :: networks (MACNET), which utilize directed acyclic graphs to organize agents and streamline their interactive reasoning via topological ordering, with solutions derived from their dialogues. Extensive experiments show that MACNET consistently outperforms baseline models, en- abling effective agent collaboration across var- ious network topologies and supporting coop- eration among more than a thousand agents. Notably, we observed a small-world collabo- ration phenomenon, where topologies resem- bling small-world properties achieved supe- rior performance. Additionally, we identified a collaborative scaling law, indicating that normalized solution quality follows a logistic growth pattern as scaling agents, with collabo- rative emergence occurring much earlier than previously observed instances of neural emer- gence. The code and data will be available at https://github.com/OpenBMB/ChatDev.	https://arxiv.org/abs/2406.07155	Organization	Artificial Intelligence (cs.AI)	scaling_large-language-model-based_multi-agent_collaboration_20240611	Tsinghua University, Beijing University of Posts and Telecommunications
90	Scaling Large-Language-Model-based Multi-Agent Collaboration	Chen Qian, Zihao Xie, Yifei Wang, Wei Liu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, Maosong Sun	2024.6.11	Pioneering advancements in large language model-powered agents have underscored the design pattern of multi-agent collaboration, demonstrating that collective intelligence can surpass the capabilities of each individual. In- spired by the neural scaling law, which posits that increasing neurons leads to emergent abil- ities, this study investigates whether a simi- lar principle applies to increasing agents in multi-agent collaboration. Technically, we propose ::multi-agent :collaboration :: networks (MACNET), which utilize directed acyclic graphs to organize agents and streamline their interactive reasoning via topological ordering, with solutions derived from their dialogues. Extensive experiments show that MACNET consistently outperforms baseline models, en- abling effective agent collaboration across var- ious network topologies and supporting coop- eration among more than a thousand agents. Notably, we observed a small-world collabo- ration phenomenon, where topologies resem- bling small-world properties achieved supe- rior performance. Additionally, we identified a collaborative scaling law, indicating that normalized solution quality follows a logistic growth pattern as scaling agents, with collabo- rative emergence occurring much earlier than previously observed instances of neural emer- gence. The code and data will be available at https://github.com/OpenBMB/ChatDev.	https://arxiv.org/abs/2406.07155	Communication	Artificial Intelligence (cs.AI)	scaling_large-language-model-based_multi-agent_collaboration_20240611	Tsinghua University, Beijing University of Posts and Telecommunications
91	Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization	Yoichi Ishibashi, Yoshimasa Nishimura	2024.4.2	Recent advancements in automatic code gener- ation using large language model (LLM) agent have brought us closer to the future of auto- mated software development. However, exist- ing single-agent approaches face limitations in generating and improving large-scale, com- plex codebases due to constraints in context length. To tackle this challenge, we propose Self-Organized multi-Agent framework (SoA), a novel multi-agent framework that enables the scalable and efficient generation and optimiza- tion of large-scale code. In SoA, self-organized agents operate independently to generate and modify code components while seamlessly col- laborating to construct the overall codebase. A key feature of our framework is the automatic multiplication of agents based on problem com- plexity, allowing for dynamic scalability. This enables the overall code volume to be increased indefinitely according to the number of agents, while the amount of code managed by each agent remains constant. We evaluate SoA on the HumanEval benchmark and demonstrate that, compared to a single-agent system, each agent in SoA handles significantly less code, yet the overall generated code is substantially greater. Moreover, SoA surpasses the powerful single-agent baseline by 5%......	https://arxiv.org/abs/2404.02183	Organization	Software Engineering (cs.SE)	self-organized_agents_a_llm_20240402	TsukushiAI
92	Simulating Opinion Dynamics with Networks of LLM-based Agents	Yun-Shiuan Chuang, Agam Goyal, Nikunj Harlalka, Siddharth Suresh, Robert Hawkins, Sijia Yang, Dhavan Shah, Junjie Hu, Timothy T. Rogers	2023.11.16	Accurately simulating human opinion dynam- ics is crucial for understanding a variety of soci- etal phenomena, including polarization and the spread of misinformation. However, the agent- based models (ABMs) commonly used for such simulations often over-simplify human behav- ior. We propose a new approach to simulat- ing opinion dynamics based on populations of Large Language Models (LLMs). Our findings reveal a strong inherent bias in LLM agents to- wards producing accurate information, leading simulated agents to consensus in line with sci- entific reality. This bias limits their utility for understanding resistance to consensus views on issues like climate change. After induc- ing confirmation bias through prompt engineer- ing, however, we observed opinion fragmenta- tion in line with existing agent-based modeling and opinion dynamics research. These insights highlight the promise and limitations of LLM agents in this domain and suggest a path for- ward: refining LLMs with real-world discourse to better simulate the evolution of human be- liefs.	https://arxiv.org/abs/2311.09618	Simulation	Physics and Society (physics.soc-ph)	simulating_opinion_dynamics_with_20231116	University of Wisconsin-Madison
93	Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms	Petter Törnberg, Diliara Valeeva, Justus Uitermark, Christopher Bail	2023.10.5	. Social media is often criticized for amplifying toxic discourse and discouraging constructive conversa- tions. But designing social media platforms to promote better conversations is inherently challenging. This paper asks whether simulating social media through a combina- tion of Large Language Models (LLM) and Agent-Based Modeling can help researchers study how different news feed algorithms shape the quality of online conversations. We create realistic personas using data from the Ameri- can National Election Study to populate simulated social media platforms. Next, we prompt the agents to read and share news articles — and like or comment upon each other’s messages — within three platforms that use different news feed algorithms. In the first platform, users see the most liked and commented posts from users whom they follow. In the second, they see posts from all users — even those outside their own network. The third platform employs a novel “bridging” algorithm that highlights posts that are liked by people with opposing political views. We find this bridging algorithm promotes more constructive, non-toxic, conversation across political divides than the other two models. Though further research is needed to evaluate these findings, we argue that LLMs hold consid- erable potential to improve simulation research on social media and many other complex social settings.	https://arxiv.org/abs/2310.05984	Simulation	Social and Information Networks (cs.SI)	simulating_social_media_using_20231005	University of Amsterdam, Duke University
94	Social Simulacra: Creating Populated Prototypes for Social Computing Systems	Joon Sung Park, Lindsay Popowski, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein	2022.8.8	Social computing prototypes probe the social behaviors that may arise in an envisioned system design. This prototyping practice is currently limited to recruiting small groups of people. Unfortu- nately, many challenges do not arise until a system is populated at a larger scale. Can a designer understand how a social system might behave when populated, and make adjustments to the de- sign before the system falls prey to such challenges? We intro- duce social simulacra, a prototyping technique that generates a breadth of realistic social interactions that may emerge when a so- cial computing system is populated. Social simulacra take as input the designer’s description of a community’s design—goal, rules, and member personas—and produce as output an instance of that design with simulated behavior, including posts, replies, and anti-social behaviors. We demonstrate that social simulacra shift the behaviors that they generate appropriately in response to design changes, and that they enable exploration of “what if?” scenarios where commu- nity members or moderators intervene. To power social simulacra, we contribute techniques for prompting a large language model to generate thousands of distinct community members and their social interactions with each other; these techniques are enabled by the observation that large language models’ training data already includes a wide variety of positive and negative behavior on social media platforms. In evaluations, we show that participants are of- ten unable to distinguish social simulacra from actual community behavior and that social computing designers successfully refine their social computing designs when using social simulacra.	https://arxiv.org/abs/2208.04024	Simulation	Human-Computer Interaction (cs.HC)	social_simulacra_creating_populated_20220808	Stanford University, Google Research
95	StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving	Chang Gao, Haiyun Jiang, Deng Cai, Shuming Shi, Wai Lam	2023.11.15	Most existing prompting methods suffer from the issues of generalizability and consistency, as they often rely on instance-specific solutions that may not be applicable to other instances and lack task-level consistency across the selected few-shot examples. To address these limitations, we propose a comprehensive framework, StrategyLLM, allowing LLMs to perform inductive reasoning, deriving general strategies from specific task instances, and deductive reasoning, applying these general strategies to particular task examples, for constructing generalizable and consistent few-shot prompts. It employs four LLM-based agents: strategy generator, executor, optimizer, and evaluator, working together to generate, evaluate, and select promising strategies for a given task. Experimental results demonstrate that StrategyLLM outperforms the competitive baseline CoT-SC that requires human-annotated solutions on 13 datasets across 4 challenging tasks without human involvement, including math reasoning (34.2\% → 38.8\%), commonsense reasoning (70.3\% → 72.5\%), algorithmic reasoning (73.7\% → 85.0\%), and symbolic reasoning (30.0\% → 79.2\%). Further analysis reveals that StrategyLLM is applicable to various LLMs and demonstrates advantages across numerous scenarios.	https://arxiv.org/abs/2311.08803	Organization	Computation and Language (cs.CL)	strategyllm_large_language_models_20231115	The Chinese University of Hong Kong, Sun Yat-sen University, Tencent AI Lab
96	The Impact of Language on Arithmetic Proficiency- A Multilingual Investigation with Cross-Agent Checking Computation	Chung-Chi Chen, Hiroya Takamura, Ichiro Kobayashi, Yusuke Miyao	2024.6.16	This paper critically examines the arithmetic capabilities of Large Language Models (LLMs), uncovering significant limitations in their performance. Our research reveals a notable decline in accuracy for complex calculations involving large numbers, with addition and subtraction tasks showing varying degrees of proficiency. Additionally, we challenge the notion that arithmetic is language-independent, finding up to a 10% difference in performance across twenty languages. The study also compares self-verification methods with cross-agent collaborations, showing that a single model often outperforms collaborative approaches in basic arithmetic tasks. These findings suggest a need to reassess the effectiveness of LLMs in tasks requiring numerical accuracy and precision.	https://aclanthology.org/2024.naacl-short.53.pdf	Communication		the_impact_of_language_20240616	AIST, University of Tokyo
97	The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents	Yun-Shiuan Chuang, Siddharth Suresh, Nikunj Harlalka, Agam Goyal, Robert Hawkins, Sijia Yang, Dhavan Shah, Junjie Hu, Timothy T. Rogers	2023.11.16	Human groups are able to converge on more accurate beliefs through deliberation, even in the presence of polarization and partisan bias — a phenomenon known as the “wisdom of partisan crowds.” Generated agents powered by Large Language Models (LLMs) are increasingly used to simulate human collective behavior, yet few benchmarks exist for evaluating their dynamics against the behavior of hu- man groups. In this paper, we examine the extent to which the wisdom of partisan crowds emerges in groups of LLM-based agents that are prompted to role-play as partisan personas (e.g., Democrat or Republican). We find that they not only display human-like partisan biases, but also converge to more accurate beliefs through deliberation as humans do. We then identify several factors that interfere with convergence, including the use of chain-of-thought prompt and lack of details in personas. Conversely, fine-tuning on human data appears to enhance conver- gence. These findings show the potential and limitations of LLM-based agents as a model of human collective intelligence.	https://arxiv.org/abs/2311.09665	Simulation	Computation and Language (cs.CL)	the_wisdom_of_partisan_20231116	University of Wisconsin-Madison
98	Theory of Mind for Multi-Agent Collaboration via Large Language Models	Huao Li, Yu Quan Chong, Simon Stepputtis, Joseph Campbell, Dana Hughes, Michael Lewis, Katia Sycara	2023.10.16	While Large Language Models (LLMs) have demonstrated impressive accomplishments in both reasoning and planning, their abilities in multi-agent collaborations remains largely unexplored. This study evaluates LLM- based agents in a multi-agent cooperative text game with Theory of Mind (ToM) inference tasks, comparing their performance with Multi- Agent Reinforcement Learning (MARL) and planning-based baselines. We observed evi- dence of emergent collaborative behaviors and high-order Theory of Mind capabilities among LLM-based agents. Our results reveal limi- tations in LLM-based agents’ planning opti- mization due to systematic failures in managing long-horizon contexts and hallucination about the task state. We explore the use of explicit belief state representations to mitigate these is- sues, finding that it enhances task performance and the accuracy of ToM inferences for LLM- based agents.	https://arxiv.org/abs/2310.10701	Communication	Computation and Language (cs.CL)	theory_of_mind_for_20231016	University of Pittsburgh, Carnegie Mellon University
99	To Infinity and Beyond- SHOW-1 and Showrunner Agents in Multi-Agent Simulations	Philipp Maas, Frank Carey, Chris Wheeler, Edward Saatchi, Pete Billington, Jessica Yaffa Shamash	2023.7.24	In this work we present our approach to generating high-quality episodic content for IP’s (Intellectual Property) using large language models (LLMs), custom state-of- the art diffusion models and our multi-agent simulation for contextualization, story progression and behavioral control. Powerful LLMs such as GPT-4 were trained on a large corpus of TV show data which lets us believe that with the right guidance users will be able to rewrite entire seasons."That Is What Entertainment Will Look Like. Maybe people are still upset about the last season of Game of Thrones. Imagine if you could ask your A.I. to make a new ending that goes a different way and maybe even put yourself in there as a main character or something.”.	https://fablestudio.github.io/showrunner-agents/static/pdfs/To_Infinity_and_Beyond_SHOW-1_And_Showrunner_Agents_in_Multi_Agent_Simulations_v2.pdf	Simulation		to_infinity_and_beyond_20230724	Fable Studio
100	Toward Optimal LLM Alignments Using Two-Player Games	Rui Zheng, Hongyi Guo, Zhihan Liu, Xiaoying Zhang, Yuanshun Yao, Xiaojun Xu, Zhaoran Wang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Hang Li, Yang Liu	2024.6.16	Alignment of large language models is a critical process designed to ensure that the model’s responses to user prompts accurately reflect human intentions and adhere to societal values. The standard Reinforcement Learning from Human Feedback (RLHF) framework primarily focuses on optimizing the performance of large language models using pre-collected prompts. However, collecting prompts that provide comprehensive coverage is both tedious and challenging, and often fails to include scenarios that LLMs need to improve on the most. In this paper, we investigate alignment through the lens of two-agent games, involving iterative interactions between an adversarial and a defensive agent. The adversarial agent’s task at each step is to generate prompts that expose the weakness of the defensive agent. In return, the defensive agent seeks to improve its responses to these newly identified prompts it “struggled" with, based on feedback from the reward model. We theoretically demonstrate that this iterative reinforcement learning optimization converges to a Nash Equilibrium for the game induced by the agents. Experi- mental results in safety scenarios demonstrate that learning in such a competitive environment not only fully trains agents but also leads to policies with enhanced generalization capabilities for both adversarial and defensive agents. Our code is released at https://github.com/ruizheng20/gpo.	https://arxiv.org/abs/2406.10977	Communication	Computation and Language (cs.CL)	toward_optimal_llm_alignments_20240616	Fudan University, Northwestern University, ByteDance Research
101	Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework	Xiaoxi Sun, Jinpeng Li, Yan Zhong, Dongyan Zhao, Rui Yan	2024.6.5	The advent of large language models (LLMs) has facilitated the development of natural lan- guage text generation. It also poses unprece- dented challenges, with content hallucination emerging as a significant concern. Existing solutions often involve expensive and complex interventions during the training process. More- over, some approaches emphasize problem dis- assembly while neglecting the crucial valida- tion process, leading to performance degrada- tion or limited applications. To overcome these limitations, we propose a Markov Chain-based multi-agent debate verification framework to enhance hallucination detection accuracy in concise claims. Our method integrates the fact- checking process, including claim detection, evidence retrieval, and multi-agent verification. In the verification stage, we deploy multiple agents through flexible Markov Chain-based debates to validate individual claims, ensuring meticulous verification outcomes. Experimen- tal results across three generative tasks demon- strate that our approach achieves significant improvements over baselines.	https://arxiv.org/abs/2406.03075	Communication	Computation and Language (cs.CL)	towards_detecting_llms_hallucination_20240605	Peking University, Renmin University of China
102	TraveLER: A Multi-LMM Agent Framework for Video Question-Answering	Chuyi Shang, Amos You, Sanjay Subramanian, Trevor Darrell, Roei Herzig	2024.4.1	Recently, Large Multimodal Models (LMMs) have made significant progress in video question-answering using a frame-wise approach by leveraging large-scale, image-based pretraining in a zero-shot manner. While image- based methods for videos have shown impressive performance, a current limitation is that they often overlook how key timestamps are selected and cannot adjust when incorrect timestamps are identified. Moreover, they are unable to extract details relevant to the question, instead providing general descriptions of the frame. To overcome this, we design a multi-LMM agent framework that travels along the video, iteratively collecting relevant in- formation from keyframes through interactive question-asking until there is sufficient information to answer the question. Specifically, we propose TraveLER, a model that can create a plan to “Traverse” through the video, ask questions about individual frames to “Locate” and store key informa- tion, and then “Evaluate” if there is enough information to answer the question. Finally, if there is not enough information, our method is able to “Replan” based on its collected knowledge. Through extensive experiments, we find that the proposed TraveLER approach improves performance on several video question-answering benchmarks, such as NExT-QA, STAR, and Perception Test, without the need to fine-tune on specific datasets.	https://arxiv.org/abs/2404.01476	Organization	Computer Vision and Pattern Recognition (cs.CV)	traveler_a_multi-lmm_agent_20240401	University of California, Berkeley
103	Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration	Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, Heng Ji	2023.7.11	Human intelligence thrives on cognitive syn- ergy, where collaboration among different minds yield superior outcomes compared to iso- lated individuals. In this work, we propose Solo Performance Prompting (SPP), which trans- forms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas. A cognitive syner- gist is an intelligent agent that collaboratively combines multiple minds’ strengths and knowl- edge to enhance problem-solving in complex tasks. By dynamically identifying and simu- lating different personas based on task inputs, SPP unleashes the potential of cognitive syn- ergy in LLMs. Our in-depth analysis shows that assigning multiple fine-grained personas in LLMs improves problem-solving abilities compared to using a single or fixed number of personas. We evaluate SPP on three chal- lenging tasks: Trivia Creative Writing, Code- names Collaborative, and Logic Grid Puzzle, encompassing both knowledge-intensive and reasoning-intensive types. Unlike previous works, such as Chain-of-Thought, that solely enhance the reasoning abilities in LLMs, ex- perimental results demonstrate that SPP effec- tively reduces factual hallucination, and main- tains strong reasoning capabilities. Addition- ally, comparative experiments show that cog- nitive synergy only emerges in GPT-4 and does not appear in less capable models, such as GPT-	https://arxiv.org/abs/2307.05300	Organization	Artificial Intelligence (cs.AI)	unleashing_the_emergent_cognitive_20230711	University of Illinois Urbana-Champaign, Microsoft Research Asia
104	Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulation	Xinyi Mou, Zhongyu Wei, Xuanjing Huang	2024.2.26	Social media has emerged as a cornerstone of social movements, wielding significant influ- ence in driving societal change. Simulating the response of the public and forecasting the potential impact has become increasingly im- portant. However, existing methods for simu- lating such phenomena encounter challenges concerning their efficacy and efficiency in cap- turing the behaviors of social movement par- ticipants. In this paper, we introduce a hybrid framework HiSim for social media user simu- lation, wherein users are categorized into two types. Core users are driven by Large Lan- guage Models, while numerous ordinary users are modeled by deductive agent-based models. We further construct a Twitter-like environment to replicate their response dynamics following trigger events. Subsequently, we develop a multi-faceted benchmark SoMoSiMu-Bench for evaluation and conduct comprehensive ex- periments across real-world datasets. Exper- imental results demonstrate the effectiveness and flexibility of our method	https://arxiv.org/abs/2402.16333	Simulation	Computers and Society (cs.CY)	unveiling_the_truth_and_20240226	Fudan University, Shanghai Collaborative Innovation Center of Intelligent Visual Computing
105	User Behavior Simulation with Large Language Model based Agents	Lei Wang, Jingsen Zhang, Hao Yang, Zhiyuan Chen, Jiakai Tang, Zeyu Zhang, Xu Chen, Yankai Lin, Ruihua Song, Wayne Xin Zhao, Jun Xu, Zhicheng Dou, Jun Wang, Ji-Rong Wen	2023.6.5	Simulating high quality user behavior data has always been a fundamental problem in human-centered applications, where the major difficulty originates from the intricate mechanism of human decision process. Recently, substantial evidences have suggested that by learning huge amounts of web knowledge, large language models (LLMs) can achieve human-like intelligence. We believe these models can provide significant opportunities to more believable user behavior simulation. To inspire such direction, we propose an LLM-based agent framework and design a sandbox environment to simulate real user behaviors. Based on extensive experiments, we find that the simulated behaviors of our method are very close to the ones of real humans. Concerning potential applications, we simulate and study two social phenomenons including (1) information cocoons and (2) user conformity behaviors. This research provides novel simulation paradigms for human-centered applications.	https://arxiv.org/abs/2306.02552	Organization	Information Retrieval (cs.IR)	user_behavior_simulation_with_20230605	Renmin University of China, Beijing Key Laboratory of Big Data Management and Analysis Methods, University College London
106	User Behavior Simulation with Large Language Model based Agents	Lei Wang, Jingsen Zhang, Hao Yang, Zhiyuan Chen, Jiakai Tang, Zeyu Zhang, Xu Chen, Yankai Lin, Ruihua Song, Wayne Xin Zhao, Jun Xu, Zhicheng Dou, Jun Wang, Ji-Rong Wen	2023.6.5	Simulating high quality user behavior data has always been a fundamental problem in human-centered applications, where the major difficulty originates from the intricate mechanism of human decision process. Recently, substantial evidences have suggested that by learning huge amounts of web knowledge, large language models (LLMs) can achieve human-like intelligence. We believe these models can provide significant opportunities to more believable user behavior simulation. To inspire such direction, we propose an LLM-based agent framework and design a sandbox environment to simulate real user behaviors. Based on extensive experiments, we find that the simulated behaviors of our method are very close to the ones of real humans. Concerning potential applications, we simulate and study two social phenomenons including (1) information cocoons and (2) user conformity behaviors. This research provides novel simulation paradigms for human-centered applications.	https://arxiv.org/abs/2306.02552	Simulation	Information Retrieval (cs.IR)	user_behavior_simulation_with_20230605	Renmin University of China, Beijing Key Laboratory of Big Data Management and Analysis Methods, University College London
107	Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies	Gati Aher, Rosa I. Arriaga, Adam Tauman Kalai	2022.8.18	We introduce a new type of test, called a Turing Experiment (TE), for evaluating to what extent a given language model, such as GPT models, can simulate different aspects of human behavior. A TE can also reveal consistent distortions in a language model's simulation of a specific human behavior. Unlike the Turing Test, which involves simulating a single arbitrary individual, a TE requires simulating a representative sample of participants in human subject research. We carry out TEs that attempt to replicate well-established findings from prior studies. We design a methodology for simulating TEs and illustrate its use to compare how well different language models are able to reproduce classic economic, psycholinguistic, and social psychology experiments: Ultimatum Game, Garden Path Sentences, Milgram Shock Experiment, and Wisdom of Crowds. In the first three TEs, the existing findings were replicated using recent models, while the last TE reveals a "hyper-accuracy distortion" present in some language models (including ChatGPT and GPT-4), which could affect downstream applications in education and the arts.	https://arxiv.org/abs/2208.10264	Simulation	Computation and Language (cs.CL)	using_large_language_models_20220818	Olin College of Engineering, Georgia Tech, Microsoft Research
108	War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars	Wenyue Hua, Lizhou Fan, Lingyao Li, Kai Mei, Jianchao Ji, Yingqiang Ge, Libby Hemphill, Yongfeng Zhang	2023.11.28	Can we avoid wars at the crossroads of history? This question has been pursued by individuals, scholars, policymakers, and organizations throughout human history. In this research, we attempt to answer the question based on the recent advances of Artificial Intelligence (AI) and Large Language Models (LLMs). We propose WarAgent, an LLM-powered multi-agent AI system, to simulate the participating countries, their decisions, and the consequences, in historical international conflicts, including the World War I (WWI), the World War II (WWII), and the Warring States Period (WSP) in Ancient China. By evaluating the simulation effectiveness, we examine the advancements and limitations of cutting-edge AI systems’ abilities in studying complex collective human behaviors such as international conflicts under diverse settings. In these simulations, the emergent interactions among agents also offer a novel perspective for examining the triggers and conditions that lead to war. Our findings offer data-driven and AI-augmented insights that can redefine how we approach conflict resolution and peacekeeping strategies. The implications stretch beyond historical analysis, offering a blueprint for using AI to understand human history and possibly prevent future international conflicts. Code and data are available at https://github.com/agiresearch/WarAgent.	https://arxiv.org/abs/2311.17227	Simulation	Artificial Intelligence (cs.AI)	war_and_peace_(waragent)_20231128	Rutgers University
109	War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars	Wenyue Hua, Lizhou Fan, Lingyao Li, Kai Mei, Jianchao Ji, Yingqiang Ge, Libby Hemphill, Yongfeng Zhang	2023.11.28	Can we avoid wars at the crossroads of history? This question has been pursued by individuals, scholars, policymakers, and organizations throughout human history. In this research, we attempt to answer the question based on the recent advances of Artificial Intelligence (AI) and Large Language Models (LLMs). We propose WarAgent, an LLM-powered multi-agent AI system, to simulate the participating countries, their decisions, and the consequences, in historical international conflicts, including the World War I (WWI), the World War II (WWII), and the Warring States Period (WSP) in Ancient China. By evaluating the simulation effectiveness, we examine the advancements and limitations of cutting-edge AI systems’ abilities in studying complex collective human behaviors such as international conflicts under diverse settings. In these simulations, the emergent interactions among agents also offer a novel perspective for examining the triggers and conditions that lead to war. Our findings offer data-driven and AI-augmented insights that can redefine how we approach conflict resolution and peacekeeping strategies. The implications stretch beyond historical analysis, offering a blueprint for using AI to understand human history and possibly prevent future international conflicts. Code and data are available at https://github.com/agiresearch/WarAgent.	https://arxiv.org/abs/2311.17227	Organization	Artificial Intelligence (cs.AI)	war_and_peace_(waragent)_20231128	Rutgers University