README.md

Awesome Multi-Agent Papers

A compilation of the best multi-agent papers

🐦 Twitter   •   📢 Discord   •   Swarms Platform   •   📙 Framework

A compilation of the best multi-agent papers by the Swarms Team. Our mission is to democratize multi-agent systems to automate the world economy with agents and usher in a post-scarcity Human civilization. Join our community now!

Format

• [ Paper Name ] [ PDF ] [ PAPER LINK ]

---

Papers

• [ K-Level Reasoning with Large Language Models ] [ PDF LINK ]

• [ More agents is all you need ] [ PDF LINK]

• [ LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration ] [ PDF LINK]

• [ Automated Unit Test Improvement using Large Language Models ] [ PDF LINK ]

• [ Human-level play in the game of Diplomacy by combining language models with strategic reasoning ] [ PDF LINK]

• [ AgentScope: A Flexible yet Robust Multi-Agent Platform ] [ PDF] ]

• [ Experiential Co-Learning of Software-Developing Agents ] [ PDF LINK ]

• [ Communicative Agents for Software Development] [ PDF LINK ]

• [ Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Match Human Crowd Accuracy ] [ PDF LINK ]

• [ Generative Agents: Interactive Simulacra of Human Behavior ] [ PDF LINK]

• [ Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems ] [ PDF LINK ]

• [ Learning to Decode Collaboratively with Multiple Language Models ] [ PDF LINK]

• [ SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents ][ PDF LINK ]

• [ Mora: Enabling Generalist Video Generation via A Multi-Agent Framework ] PDF LINK ]

• [ LLM Agent Operating System ] [ PDF LINK ]

• [ MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution ] [ PDF LINK ]

• [ AllHands: Ask Me Anything on Large-scale Verbatim Feedback via Large Language Models ] [ PDF LINK ]

• [ Scaling Instructable Agents Across Many Simulated Worlds ] [ PDF LINK ]

• [ Evolutionary Optimization of Model Merging Recipes ][ PDF LINK ]

• [ Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models ] PDF LINK]

• [ Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents ] [ PDF LINK ]

• [ AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation ] [ PDF LINK]

• [ Chain of Agents: Large Language Models Collaborating on Long-Context Tasks] [PDF LINK ]

• [ CulturePark: Boosting Cross-cultural Understanding in Large Language Models] [PDF LINK]

• [ Constitutional AI: Harmlessness from AI Feedback ] [ [PDF Link]

• [ Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration ] [ PDF LINK]

• Mixture-of-Agents Enhances Large Language Model Capabilities

• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments

• [ CODER: ISSUE RESOLVING WITH MULTI-AGENT AND TASK GRAPHS] PDF LINK

• EVOAGENT: Towards Automatic Multi-Agent: Generation via Evolutionary Algorithms

• Scaling Synthetic Data Creation with 1,000,000,000 Personas

• (Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts

• RouteLLM: An Open-Source Framework for Cost-Effective LLM Routing

• On scalable oversight with weak LLMs judging strong LLMs

• AgentInstruct: Toward Generative Teaching with Agentic Flows

• On scalable oversight with weak LLMs judging strong LLMs

• Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents

• Very Large-Scale Multi-Agent Simulation in AgentScope

• Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents

• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence

• LAMBDA: A Large Model Based Data Agent

• DIFFUSION AUGMENTED AGENTS: A FRAMEWORK FOR EFFICIENT EXPLORATION AND TRANSFER LEARNING

• From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models

• Mindstorms in Natural Language-Based Societies of Mind

• Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning

• ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate

• [CL] From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future][https://arxiv.org/abs/2408.02479]

• Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks

• The AI Scientist: The world’s first AI system for automating scientific research and open-ended discovery!

• CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases

• Integrating Expertise of Software Engineering Agents

  • Removed the first acouple words because their woke and communist propaganda, only reason I'm adding it is because it beats SOTA

• Automated Design of Agentic Systems

• The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization Dataset Generation

• MEDCO: Medical Education Copilots Based on A Multi-Agent Framework

• Agentic Retrieval-Augmented Generation for Time Series Analysis

• Optimizing Collaboration of LLM based Agents for Finite Element

• BreachSeek: A Multi-Agent Automated Penetration Tester

• SCIAGENTS: AUTOMATING SCIENTIFIC DISCOVERY THROUGH MULTI-AGENT INTELLIGENT GRAPH REASONING ∗_

• Large Language Model-Based Agents for Software Engineering: A Survey

• SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning

---

Todo

• Create a citations section with citations for every paper!

Community

Join the multi-agent community now on discord HERE

Citations

@misc{ong2024routellmlearningroutellms,
      title={RouteLLM: Learning to Route LLMs with Preference Data},
      author={Isaac Ong and Amjad Almahairi and Vincent Wu and Wei-Lin Chiang and Tianhao Wu and Joseph E. Gonzalez and M Waleed Kadous and Ion Stoica},
      year={2024},
      eprint={2406.18665},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2406.18665},
}

@misc{chiang2024chatbot,
    title={Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference},
    author={Wei-Lin Chiang and Lianmin Zheng and Ying Sheng and Anastasios Nikolas Angelopoulos and Tianle Li and Dacheng Li and Hao Zhang and Banghua Zhu and Michael Jordan and Joseph E. Gonzalez and Ion Stoica},
    year={2024},
    eprint={2403.04132},
    archivePrefix={arXiv},
    primaryClass={cs.AI}
}

@misc{li2024optimus1hybridmultimodalmemory,
      title={Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks}, 
      author={Zaijing Li and Yuquan Xie and Rui Shao and Gongwei Chen and Dongmei Jiang and Liqiang Nie},
      year={2024},
      eprint={2408.03615},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2408.03615}, 
}

@misc{ghafarollahi2024sciagentsautomatingscientificdiscovery,
      title={SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning}, 
      author={Alireza Ghafarollahi and Markus J. Buehler},
      year={2024},
      eprint={2409.05556},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2409.05556}, 
}