mlsanityData to 14 Oct 2026

Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game

arXiv 2310.18940 ↗First posted 29 Oct 2023cs.AI cs.LG cs.MAcited by 152

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

Agents built with large language models (LLMs) have shown great potential across a wide range of domains. However, in complex decision-making tasks, pure LLM-based agents tend to exhibit intrinsic bias in their choice of actions, which is inherited from the model's training data and results in suboptimal performance. To develop strategic language agents, i.e., agents that generate flexible language actions and possess strong decision-making abilities, we propose a novel framework that powers LLM-based agents with reinforcement learning (RL). We consider Werewolf, a popular social deduction game, as a challenging testbed that emphasizes versatile communication and strategic gameplay. To mitigate the intrinsic bias in language actions, our agents use an LLM to perform deductive reasoning and generate a diverse set of action candidates. Then an RL policy trained to optimize the decision-making ability chooses an action from the candidates to play in the game. Extensive experiments show that our agents overcome the intrinsic bias and outperform existing LLM-based agents in the Werewolf game. We also conduct human-agent experiments and find that our agents achieve human-level performance and demonstrate strong strategic play.

Key facts. Cited by 152 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 42 of its 63 references that are in the map. First posted on arXiv 29 Oct 2023.

Builds on

42 of 63 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-429 Sep
  2. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory25 May
  3. 2023Voyager: An Open-Ended Embodied Agent with Large Language Models25 May

Other references · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  8. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  9. 2022Emergent Abilities of Large Language Modelscited by 2,512
  10. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  11. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  12. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
27 more
  1. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  2. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  3. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  4. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  5. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  6. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
  7. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 571
  8. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 501
  9. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 439
  10. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
  11. 2023ChatGPT for Robotics: Design Principles and Model Abilitiescited by 299
  12. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 268
  13. 2023Reward Design with Language Modelscited by 261
  14. 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 241
  15. 2017DeepStack: Expert-Level Artificial Intelligence in No-Limit Pokercited by 233
  16. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 233
  17. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 172
  18. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 158
  19. 2023Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplationcited by 104
  20. 2018Deep Counterfactual Regret Minimizationcited by 103
  21. 2014Solving Large Imperfect Information Games Using CFR+cited by 78
  22. 2020Real World Games Look Like Spinning Topscited by 66
  23. 2023Strategic Reasoning with Language Modelscited by 64
  24. 2019A Generalized Training Approach for Multiagent Learningcited by 54
  25. 2023Epidemic Modeling with Generative Agentscited by 49
  26. 2019Finding Friend and Foe in Multi-Agent Gamescited by 42
  27. 2023Fictitious Cross-Play: Learning Global Nash Equilibrium in Mixed Cooperative-Competitive Gamescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 59; 2025: 54; 2026: 39.

152 papers.

Sort:

By area:

  1. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  2. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  3. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 206
  4. 2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaborationcited by 189
  5. 2024The Emerged Security and Privacy of LLM Agent: A Survey with Case Studiescited by 131
  6. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
  7. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  8. 2025Red-Teaming LLM Multi-Agent Systems via Communication Attackscited by 122
  9. 2024GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluationscited by 120
  10. 2024FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Makingcited by 113
  11. 2024A Survey on Large Language Model-Based Game Agentscited by 112
  12. 2025Multi-Agent Collaboration via Evolving Orchestrationcited by 108
38 more
  1. 2025SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learningcited by 100
  2. 2024LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Modelscited by 99
  3. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 99
  4. 2024Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimizationcited by 94
  5. 2024Embodied LLM Agents Learn to Cooperate in Organized Teamscited by 82
  6. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 82
  7. 2024Visibility into AI Agentscited by 79
  8. 2024How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environmentscited by 67
  9. 2024DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)cited by 58
  10. 2024Game-theoretic LLM: Agent Workflow for Negotiation Gamescited by 56
  11. 2025Do as We Do, Not as You Think: the Conformity of Large Language Modelscited by 53
  12. 2024When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Searchcited by 47
  13. 2024Enhance Reasoning for Large Language Models in the Game Werewolfcited by 46
  14. 2024Werewolf Arena: A Case Study in LLM Evaluation via Social Deductioncited by 45
  15. 2024ResearchTown: Simulator of Human Research Communitycited by 37
  16. 2024Do LLM Agents Have Regret? A Case Study in Online Learning and Gamescited by 35
  17. 2026Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learningcited by 31
  18. 2024PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaborationcited by 28
  19. 2024AMONGAGENTS: Evaluating Large Language Models in the Interactive Text-Based Social Deduction Gamecited by 28
  20. 2024InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Contextcited by 26
  21. 2024A Survey on Self-play Methods in Reinforcement Learningcited by 26
  22. 2024Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolfcited by 24
  23. 2024TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulationcited by 23
  24. 2024Large Language Models and Video Games: A Preliminary Scoping Reviewcited by 23
  25. 2024RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMscited by 23
  26. 2024A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarioscited by 23
  27. 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systemscited by 23
  28. 2024A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challengescited by 22
  29. 2024K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoningcited by 21
  30. 2024Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulationcited by 21
  31. 2025LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring Systemcited by 21
  32. 2024Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Searchcited by 17
  33. 2025Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancycited by 17
  34. 2025MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMscited by 16
  35. 2025Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimizationcited by 15
  36. 2025Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systemscited by 15
  37. 2026Agentic World Modeling: Foundations, Capabilities, Laws, and Beyondcited by 14
  38. 2024Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Gamecited by 13

50 most cited of 152 All 152 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024An Implementation of Werewolf Agent That does not Truly Trust LLMs
  2. 2024Large Language Models as Agents in Two-Player Games
  3. 2025WereWolf-Plus: An Update of Werewolf Game setting Based on DSGBench
  4. 2025MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind
  5. 2026Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information
  6. 2024Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information
  7. 2025Playing games with Large language models: Randomness and strategy
  8. 2026Rethinking Agentic Reinforcement Learning In Large Language Models