引用本概念的论文(2)
- 在隐藏信息社交推理游戏中审计信念条件化的大语言模型智能体 Auditing Belief-Conditioned LLM Agents in Hidden-Information Social Deduction Games arXiv 2607.10814
- MafiaScope:面向社交推理游戏中 LLM 智能体的非侵入式、时序分辨信念探测 MafiaScope: Non-Invasive, Time-Resolved Belief Probing for LLM Agents in Social Deduction Games arXiv 2607.10645