• [2023/10/22] We create this repository to maintain a paper list on LLMs for MASs.

Large Language Models (LLMs) have been widely applied to various real-world applications. Particularly, LLMs as agents have been adopted in multi-agent systems (MASs) to collaborate or compete with other agents or humans, demonstrating their amazing ability to solve real-world multi-agent problems. In this repository, we track the latest progress in LLMs for MASs and list the papers on various topics related to this field.

• LLMs for Multi-Agent Systems
  • News
  • Introduction
  • 1. Cooperative
  • 2. Competitive
  • 3. Mixed Motivate
  • 4. Mechanism Design, Economics, Sociology

• [2023/12/12] Exploring Large Language Models to Facilitate Variable Autonomy for Human-Robot Teaming. Younes Lakhnati et al. arXiv. [paper]
• [2023/12/09] Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach. Bin Zhang et al. arXiv. [paper]
• [2023/11/16] MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning. Xiangru Tang et al. arXiv. [paper] [code]
• [2023/11/14] Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration. Zhenran Xu et al. arXiv. [paper] [code]
• [2023/10/23] AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors. Weize Chen et al. arXiv. [paper] [code]
• [2023/10/22] Theory of Mind for Multi-Agent Collaboration via Large Language Models. Huao Li et al. EMNLP2023 Main Conference. [paper]
• [2023/10/15] AutoAgents: A Framework for Automatic Agent Generation. Guangyao Chen et al. arXiv. [paper] [code]
• [2023/10/08] Agents: An Open-source Framework for Autonomous Language Agents. Wangchunshu Zhou et al. arXiv. [paper] [code]
• [2023/10/05] Evaluating Multi-Agent Coordination Abilities in Large Language Models. Saaket Agashe et al. arXiv. [paper]
• [2023/10/03] Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization. Zijun Liu et al. arXiv. [paper] [code]
• [2023/10/03] AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. Qingyun Wu et al. arXiv. [paper] [code]
• [2023/08/28] CGMI: Configurable General Multi-Agent Interaction Framework. Shi Jinxin et al. arXiv. [paper]
• [2023/08/28] ProAgent: Building Proactive Cooperative AI with Large Language Models. Ceyao Zhang et al. arXiv. [paper] [code]
• [2023/08/17] MetaGPT: Meta Programming for Multi-Agent Collaborative Framework. Sirui Hong et al. arXiv. [paper] [code]
• [2023/07/10] RoCo: Dialectic Multi-Robot Collaboration with Large Language Models. Zhao Mandi et al. arXiv. [paper] [code]
• [2023/06/05] Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents. Yashar Talebirad et al. arXiv. [paper]
• [2023/05/30] Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate. Tian Liang et al. arXiv. [paper] [code]
• [2023/05/23] Improving Factuality and Reasoning in Language Models through Multiagent Debate. Yilun Du et al. arXiv. [paper] [code]
• [2023/04/24] ChatLLM Network: More brains, More intelligence. Rui Hao et al. arXiv. [paper]
• [2023/01/12] Blind Judgement: Agent-Based Supreme Court Modelling With GPT. Sil Hamilton. AAAI-23 Workshop on Creative AI Across Modalities. [paper]

• [2023/12/12] Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis. Caoyun Fan et al. AAAI2024. [paper]
• [2023/11/06] ALYMPICS: Language Agents Meet Game Theory. Shaoguang Mao et al. arXiv. [paper]
• [2023/11/06] Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models. Tian Liang et al. arXiv. [paper] [code]
• [2023/10/26] CompeteAI: Understanding the Competition Behaviors in Large Language Model-based Agents. Qinlin Zhao et al. arXiv. [paper]
• [2023/10/13] The Consensus Game: Language Model Generation via Equilibrium Search. Athul Paul Jacob et al. arXiv. [paper]
• [2023/10/10] Red Teaming Game: A Game-Theoretic Framework for Red Teaming Language Models. Chengdong Ma et al. arXiv. [paper]
• [2023/10/06] Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4. Jiaxian Guo et al. arXiv. [paper] [code]
• [2023/09/12] Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing. Nunzio Lorè et al. arXiv. [paper]
• [2023/08/23] Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis. Akshat Gupta arXiv. [paper]
• [2023/07/10] Playing Games With GPT: What Can We Learn About a Large Language Model From Canonical Strategic Games? Philip Brookins et al. SSRN. [paper] [code]
• [2023/05/30] Strategic Reasoning with Language Models. Kanishk Gandhi et al. arXiv. [paper]
• [2023/05/26] Playing repeated games with Large Language Models. Elif Akata et al. arXiv. [paper]
• [2023/05/09] GPT Agents in Game Theory Experiments. Fulin Guo. arXiv. [paper]
• [2023/03/02] Population-based Evaluation in Repeated Rock-Paper-Scissors as a Benchmark for Multiagent Reinforcement Learning. Marc Lanctot et al. arXiv. [paper]
• [2022/11/22] Human-Level Play in the Game of Diplomacy by Combining Language Models with Strategic Reasoning. Anton Bakhtin et al. Science. [paper] [code]

• [2023/12/01] Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games. Dekun Wu et al. arXiv. [paper]
• [2023/11/28] War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars. Wenyue Hua et al. arXiv. [paper] [code]
• [2023/11/16] MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration. Lin Xu et al. arXiv. [paper] [code]
• [2023/11/09] Long-Horizon Dialogue Understanding for Role Identification in the Game of Avalon with Large Language Models. Simon Stepputtis et al. EMNLP2023, Findings of the Association for Computational Linguistics. [paper] [code]
• [2023/10/24] Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation. Shenzhi Wang et al. arXiv. [paper]
• [2023/10/23] LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay. Yihuai Lan et al. arXiv. [paper]
• [2023/10/13] Welfare Diplomacy: Benchmarking Language Model Cooperation. Gabriel Mukobi et al. arXiv. [paper] [code]
• [2023/10/08] From Text to Tactic: Evaluating LLMs Playing the Game of Avalon. Jonathan Light et al. arXiv. [paper] [code]
• [2023/09/06] Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf. Yuzhuang Xu et al. arXiv. [paper]

• [2023/10/16] Mechanism Design for Large Language Models. Paul Duetting et al. arXiv. [paper]
• [2023/10/09] Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena. Jiangjie Chen et al. arXiv. [paper] [code]
• [2023/10/03] Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View. Jintian Zhang et al. arXiv. [paper] [code]
• [2023/05/23] Human Choice Prediction in Language-based Non-Cooperative Games: Simulation-based Off-Policy Evaluation. Eilam Shapira et al. arXiv. [paper]
• [2023/05/13] Investigating Emergent Goal-Like Behaviour in Large Language Models Using Experimental Economics. Steve Phelps et al. arXiv. [paper]