作者位次 #2/5ACL 2026Poster· Natural Language Processing
M em B uilder: Reinforcing LLM s for Long-Term Memory Construction via Attributed Dense Rewards
Zhiyu Shen · Ziming Wu · Fuming Lai · Shaobing Lian · Yanghui Rao
摘要
Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the temporal evolution of historical states. While memory-augmented frameworks offer a structured alternative, current systems rely on static prompting o...