逃离自我确认陷阱:Agent经验学习的执行-蒸馏-验证新范式
Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning 作者:Shiding Zhu, Yudi Qi, Yajie Wang, Jiaze Li, Chao Song, Yaorui Shi, Yibo Miao, Hanqi Gao, Kai Zhang 核心发表机构:Zhejiang Univ…
2026/8/8 6:36:26