← back
arXivYe Yuan, Rui Song, Weien Li, Zeyu Li, Haochen Liu, Xiangyu Kong, Changjiang Han, Yonghan Yang, Zichen Zhao, Zixuan Dong, Fuyuan Lyu, Bowei He, Haolun Wu, Jikun Kang, Xue LiuTue, May 26, 2026, 7:19 AM PDT
score 16.4

Tool checks if AI agents lie about what they see in games

Original: QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents

Source: arxiv.org

Writing ELI5 summary…