Review
Jul 2026
Auditing Belief-Conditioned LLM Agents in Hidden-Information Social Deduction Games
An auditable framework is built that maintains an external belief state over hidden roles, logs belief updates and belief-action deviations as structured evidence, and supports a defensive offline improvement loop that reviews bad cases before any strategy change.
Yuanpeng Gao, Jiangyi Yang, Yao Zhao et al.
· 0 citations