作者位次 #4/7ACL 2026Findings· Findings of ACL
Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
Zouying Cao · Jiaji Deng · Li Yu · Weikang Zhou · Zhaoyang Liu · Bolin Ding · Hai Zhao
摘要
Procedural memory enables large language model (LLM) agents to internalize ”how-to” knowledge and thus reduce redundant trial-and-error. However, existing frameworks predominantly suffer from a ”passive accumulation” paradigm, treating memory as a static append-only archive. To bridge the gap bet...