Auditable Framework Reveals Belief-Action Gaps in LLM Agents Playing Werewolf

Jul 14, 2026

Researchers introduced an auditable framework for evaluating large language model (LLM) agents in a 9-player Werewolf social deduction game with strict information isolation. The framework logs belief updates and belief-action deviations, enabling detailed analysis of agent behavior. Results show that agents with active belief tracking achieve significantly higher good-side win rates (0.390 vs 0.205), but exhibit low direct action-belief consistency (≈0.21). The study highlights the value of external belief as an auditable cognitive baseline for agent development.

Why it matters: This work advances methods for auditing and interpreting LLM agent decisions in complex, hidden-information environments, supporting safer and more transparent agent iteration.

Full story at: arXiv Multiagent Systems ↗