ChatDev/MultiAgentEbook/index.html
2024-07-16 09:41:20 +08:00

329 lines
14 KiB
HTML

<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<meta http-equiv="Cache-Control" content="no-store">
<meta http-equiv="Pragma" content="no-cache">
<meta http-equiv="Expires" content="0">
<link rel="icon" type="image/png" sizes="32x32" href="./images/logo.png" />
<title>Multi-Agent Research Outline</title>
<link rel="preconnect" href="https://fonts.gstatic.com" />
<link href="https://fonts.googleapis.com/css2?family=Rubik:wght@400;500&display=swap" rel="stylesheet" />
<link rel="stylesheet" href="style.css" />
</head>
<body>
<header>
<div class="container">
<nav class="navbar flex">
<div class="hamburger-container">
<img src="./images/icon-hamburger.svg" class="hamburger" />
</div>
<div class="logo-container">
<img src="images/logo5.png" width="200" alt="Logo" />
</div>
<ul class="nav-list flex">
<li class="nav-item">
<a href="https://github.com/OpenBMB/ChatDev/tree/main/MultiAgentEbook" class="nav-link btn clr1">GitHub</a>
</li>
</ul>
</nav>
<div class="intro flex">
<img src="./images/bg-pattern.svg" class="bg-pattern" alt="background-pattern" />
<div class="intro-col-left">
<h1>
Comprehensive Outline of Large Language Model-based Multi-Agent Research
</h1>
<p>
This project presents an interactive eBook that compiles <b>an extensive collection of research papers on
large language model (LLM)-based multi-agent systems</b>. Organized into multiple chapters and
<b>continuously updated</b> with significant research, it strives to provide a comprehensive outline for
both researchers and enthusiasts in the field. We welcome <b>ongoing contributions</b> to expand and enhance
this resource.
</p>
<p>Initiated by the <a href="https://github.com/OpenBMB/ChatDev"><b>ChatDev</b></a> Group at Tsinghua
University.</p>
<div class="btn-group">
<a href="#book" class="btn clr2">Start Reading</a>
<a href="#more-works" class="btn clr3">Learn More</a>
</div>
</div>
<div class="intro-col-right">
<img src="./images/cover.png" alt="Cover" />
</div>
</div>
</div>
</header>
<section class="feature">
<div class="container">
<img src="./images/bg-pattern.svg" class="bg-pattern" alt="background-pattern" />
<h2 class="section-heading text-center">Multi-Agent Directions</h2>
<div class="content" align="center">
<p>
Multi-agent systems are currently classified into two categories based on whether the agents are designed to
achieve <b>specific task goals under external human instructions</b>: task-solving-oriented systems and
social-simulation-oriented systems.
</p>
</div>
<div class="tab-container">
<ul class="tab-nav flex">
<li class="active one"><b>Task Solving</b></li>
<li class="two"><b>Social Simulation</b></li>
</ul>
<div class="tab-body tab-one flex active">
<div class="tab-col-left">
<img src="./images/chatdev_cover.png" alt="Comprehensive Resources" width="552" />
</div>
<div class="tab-col-right">
<div class="content">
<p>
Task solving-oriented multi-agent systems employ autonomous agents working collaboratively to tackle
complex problems. Cutting-edge research in this direction revolves around three primary areas:
facilitating communication among agents, designing effective organizational structures for interaction,
and exploring how agents co-evolve over time.
</p>
<img src="./images/multi_agent_framework_ts.png" alt="Dataset cover" width="660" align="center" />
</div>
</div>
</div>
<div class="tab-body tab-two flex">
<div class="tab-col-left">
<img src="./images/simulation.png" alt="Community Driven" width="746" />
</div>
<div class="tab-col-right">
<div class="content">
<p>
Social simulation-oriented multi-agent systems concentrate on modeling and analyzing the social
behaviors of agents, offering valuable insights into human dynamics and enhances the ability to analyze
or predict social phenomena.
</p>
<img src="./images/multi_agent_framework_ss.png" alt="Dataset cover" width="660" align="center" />
</div>
</div>
</div>
</div>
</div>
</section>
<section class="cards_row">
<div class="container" id="book">
<h5 class="section-heading text-center">Dive into Each Chapter</h5>
<div class="content" align="center">
<p>
This ebook contains research papers on the multi-agent layer and above, organized into multiple chapters based
on proposed core technologies. Let's dive into each section.
</p>
</div>
<div class="browser-cards">
<div class="card">
<img src="./images/communication_cover.png" alt="Systems cover" />
<h4>§1: Communication</h4>
<p>facilitating agent communication</p>
<a href="communication.html" class="btn clr2">Read</a>
</div>
<div class="card">
<img src="./images/organization_cover.png" alt="Benchmark cover" />
<h4>§2: Organization</h4>
<p>organizing agents effectively</p>
<a href="organization.html" class="btn clr2">Read</a>
</div>
<div class="card">
<img src="./images/evolution_cover.png" alt="Dataset cover" />
<h4>§3: Evolution</h4>
<p>growing capabilities over time</p>
<a href="evolution.html" class="btn clr2">Read</a>
</div>
<div class="card">
<img src="./images/simulation_cover.png" alt="Systems cover" />
<h4>§4: Simulation</h4>
<p>simulating societal dynamics</p>
<a href="simulation.html" class="btn clr2">Read</a>
</div>
</div>
</div>
</section>
<section class="cards_row">
<h2 class="section-heading text-center">Learn More</h2>
<div class="content" align="center">
<p>
In addition to the aforementioned resources, we also feature recent research from our lab. If you find our work
of interest, we invite you to read, extend, or collaborate.
</p>
</div>
<div class="container" id="more-works">
<div class="browser-cards">
<div class="card">
<img src="./images/iagents_cover.png" />
<h4>iAgents</h4>
<p>Bijective Social Networks of Humans and Agents
</p>
<a href="https://arxiv.org/abs/2406.14928" class="btnsmall paper"><span class="icon"><img
src="images/pdf_normal.png" alt="PDF Icon"></span>Paper</a>
<a href="https://github.com/thinkwee/iAgents" class="btnsmall code"><span class="icon"><img
src="images/github_normal.png" alt="GitHub Icon"></span>Code</a>
</div>
<div class="card">
<img src="./images/ioa_cover.png"/>
<h4>IoA</h4>
<p>Networking Heterogeneous Agents</p>
<a href="https://arxiv.org/abs/2407.07061" class="btnsmall paper"><span class="icon"><img
src="images/pdf_normal.png" alt="PDF Icon"></span>Paper</a>
<a href="https://github.com/OpenBMB/IoA" class="btnsmall code"><span class="icon"><img
src="images/github_normal.png" alt="GitHub Icon"></span>Code</a>
</div>
<div class="card">
<img src="./images/chatdev_cover.png"/>
<h4>ChatDev</h4>
<p>Multi-Agent Collaboration for Software Development</p>
<a href="https://arxiv.org/abs/2307.07924" class="btnsmall paper"><span class="icon"><img
src="images/pdf_normal.png" alt="PDF Icon"></span>Paper</a>
<a href="https://github.com/OpenBMB/ChatDev" class="btnsmall code"><span class="icon"><img
src="images/github_normal.png" alt="GitHub Icon"></span>Code</a>
</div>
<div class="card">
<img src="./images/agentverse_cover.png"/>
<h4>AgentVerse</h4>
<p>General-Purpose Multi-Agent Framework</p>
<a href="https://arxiv.org/abs/2308.10848" class="btnsmall paper"><span class="icon"><img
src="images/pdf_normal.png" alt="PDF Icon"></span>Paper</a>
<a href="https://github.com/OpenBMB/AgentVerse" class="btnsmall code"><span class="icon"><img
src="images/github_normal.png" alt="GitHub Icon"></span>Code</a>
</div>
<div class="card">
<img src="./images/colearning_cover.png"/>
<h4>Co-Learning</h4>
<p>Cross-Task Experience Co-Leaning for Mutual Growth</p>
<a href="https://arxiv.org/abs/2312.17025" class="btnsmall paper"><span class="icon"><img
src="images/pdf_normal.png" alt="PDF Icon"></span>Paper</a>
<a href="https://github.com/OpenBMB/ChatDev" class="btnsmall code"><span class="icon"><img
src="images/github_normal.png" alt="GitHub Icon"></span>Code</a>
</div>
<div class="card">
<img src="./images/ei_cover.png"/>
<h4>Co-Evolving</h4>
<p>Continuous Experience Refinement over Time</p>
<a href="https://arxiv.org/abs/2405.04219" class="btnsmall paper"><span class="icon"><img
src="images/pdf_normal.png" alt="PDF Icon"></span>Paper</a>
<a href="https://github.com/OpenBMB/ChatDev" class="btnsmall code"><span class="icon"><img
src="images/github_normal.png" alt="GitHub Icon"></span>Code</a>
</div>
<div class="card">
<img src="./images/organization.png"/>
<h4>MacNet</h4>
<p>Exploring Collaborative Scaling Law</p>
<a href="https://arxiv.org/abs/2406.07155" class="btnsmall paper"><span class="icon"><img
src="images/pdf_normal.png" alt="PDF Icon"></span>Paper</a>
<a href="https://github.com/OpenBMB/ChatDev" class="btnsmall code"><span class="icon"><img
src="images/github_normal.png" alt="GitHub Icon"></span>Code</a>
</div>
<div class="card">
<img src="./images/ctc_cover.png"/>
<h4>CTC</h4>
<p>Cross-Team Multi-Agent Orchestration</p>
<a href="https://arxiv.org/abs/2406.08979" class="btnsmall paper"><span class="icon"><img
src="images/pdf_normal.png" alt="PDF Icon"></span>Paper</a>
<a href="https://github.com/OpenBMB/ChatDev" class="btnsmall code"><span class="icon"><img
src="images/github_normal.png" alt="GitHub Icon"></span>Code</a>
</div>
<div class="card">
<img src="./images/chateval_cover.png"/>
<h4>ChatEval</h4>
<p>Communication for Automated Evaluation</p>
<a href="https://arxiv.org/abs/2308.07201" class="btnsmall paper"><span class="icon"><img
src="images/pdf_normal.png" alt="PDF Icon"></span>Paper</a>
<a href="https://github.com/thunlp/ChatEval" class="btnsmall code"><span class="icon"><img
src="images/github_normal.png" alt="GitHub Icon"></span>Code</a>
</div>
<div class="card">
<img src="./images/autoform_cover.png"/>
<h4>AutoForm</h4>
<p>Finding Effective Communication Protocals</p>
<a href="https://arxiv.org/abs/2402.18439" class="btnsmall paper"><span class="icon"><img
src="images/pdf_normal.png" alt="PDF Icon"></span>Paper</a>
<a href="https://github.com/thunlp/AutoForm" class="btnsmall code"><span class="icon"><img
src="images/github_normal.png" alt="GitHub Icon"></span>Code</a>
</div>
</div>
</div>
</section>
<section class="faq">
<div class="container">
<h2 class="section-heading">Frequently Asked Questions</h2>
<div class="faq-container">
<div class="question">
<button>
<span>How is this ebook organized?</span>
<svg xmlns="http://www.w3.org/2000/svg" width="18" height="12">
<path fill="none" stroke="#5267DF" stroke-width="3" d="M1 1l8 8 8-8" />
</svg>
</button>
<p>
This ebook gathers leading research on LLM-powered multi-agent systems since 2023, categorized by key
perspectives in the field. As this area rapidly evolves, updates will be ongoing.
</p>
</div>
<div class="question">
<button>
<span>How can I contribute?</span>
<svg xmlns="http://www.w3.org/2000/svg" width="18" height="12">
<path fill="none" stroke="#5267DF" stroke-width="3" d="M1 1l8 8 8-8" />
</svg>
</button>
<p>
We encourage open-source collaboration on this project. You can contribute by submitting a pull request with
detailed metadata for notable papers in the <a
href="https://github.com/OpenBMB/ChatDev/tree/main/MultiAgentEbook/papers.csv">table</a>.
</p>
</div>
<div class="question">
<button>
<span>How can I download this ebook?</span>
<svg xmlns="http://www.w3.org/2000/svg" width="18" height="12">
<path fill="none" stroke="#5267DF" stroke-width="3" d="M1 1l8 8 8-8" />
</svg>
</button>
<p>
You can download all ebook content in CSV format directly from <a
href="https://github.com/OpenBMB/ChatDev/tree/main/MultiAgentEbook/papers.csv">here</a>.
</p>
</div>
</div>
</div>
</section>
<div class="attribution">
<p>
Initiated by the <a href="https://github.com/OpenBMB/ChatDev" target="_blank">ChatDev</a> Group, Tsinghua
University
<br>Contact us via <a href="mailto:qianc62@gmail.com">qianc62@gmail.com</a>
<br>
<span style="font-size: 14px;" id="busuanzi_container_site_pv">Total PV <span style="font-size: 14px;" id="busuanzi_value_site_pv"></span></span>
</p>
</div>
<script src="main.js"></script>
<script async src="//busuanzi.ibruce.info/busuanzi/2.3/busuanzi.pure.mini.js"></script>
</body>
</html>