作者位次 #3/10ACL 2026Findings· Findings of ACL
MAXS : Meta-Adaptive Exploration with LLM Agents
Jian Zhang · Zhiyuan Wang · Zhangqi Wang · Yu He · Haoran Luo · li Yuan · Lingling Zhang · Rui Mao · Haiping Zhu (Xi' · an Jiaotong University)
摘要
Large Language Model (LLM) Agents exhibit inherent reasoning abilities through the collaboration of multiple tools.However, during agent inference, existing methods often suffer from (i) locally myopic generation, due to the absence of lookahead, and (ii) trajectory instability, where minor early...