Language Agents With Reinforcement Learning For Strategic Play In The Werewolf Game

Abstract

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 th

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxu2023language

Related papers

• DVM: Towards Controllable LLM Agents In Social Deduction Games (2025)0.00
• MAGE: Meta-reinforcement Learning For Language Agents Toward Strategic Exploration And Exploitation (2026)0.00
• MARSHAL: Incentivizing Multi-agent Reasoning Via Self-play With Strategic Llms (2025)0.00
• Mental Modeling Of Reinforcement Learning Agents By Language Models (2024)0.00
• Language-driven Coordination And Learning In Multi-agent Simulation Environments (2025)0.00
• From Laws To Motivation: Guiding Exploration Through Law-based Reasoning And Rewards (2024)0.00
• Reinforcement Learning Environment With Llm-controlled Adversary In D&D 5th Edition Combat (2025)0.00
• Training Agents With Weakly Supervised Feedback From Large Language Models (2024)0.00