作者位次 #4/5ACL 2026Findings· Findings of ACL
Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games
Keyang Zhong · Junlin Xie · Hefeng Wu · Haofeng Li · Guanbin Li
摘要
Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multi-player game settings with imperfect and deceptive information. In this paper, we pick up a representative multi-player task, Murder Mystery Games, whic...