作者位次 #3/5ACL 2026Poster· Natural Language Processing
T ri E x: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLM s
Ziyi Wang · Chen Jason Zhang · Wenjun Peng · Qi Wu · Xinyu Wang
摘要
Explainability for Large Language Model (LLM) agents is especially challenging in interactive, partially observable settings, where decisions depend on evolving beliefs and other agents. We present TriEx, a tri-view explainability framework that instruments sequential decision making with aligned...