arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.13530cs.AI
收藏

REMem: 在语言代理中进行基于事件记忆的推理

REMem: Reasoning with Episodic Memory in Language Agent

The Ohio State University(俄亥俄州立大学);Intuit AI Research(Intuit AI研究)

Yiheng Shu, Saisri Padmaja Jonnalagedda, Xiang Gao, Bernal Jiménez Gutiérrez, Weijian Qi, Kamalika Das, Huan Sun, Yu Su

AI总结:

REMem通过两阶段框架提升语言代理的事件记忆构建与推理能力,显著优于现有系统。

摘要:

人类在时空背景下记住具体经历并在此基础上进行推理的能力,即事件记忆能力。相比之下,语言代理的记忆主要停留在语义层面,目前的代理尚无法有效回忆和对交互历史进行推理。我们从这一差距中识别并正式化了事件回忆和推理的核心挑战,并观察到现有工作往往忽视事件性、缺乏显式事件建模或过分强调简单的检索而非复杂的推理。我们提出了REMem,一种用于构建和推理事件记忆的两阶段框架:1)离线索引,其中REMem将经历转换为一种混合记忆图,能够灵活地连接时间感知的概要和事实。2)在线推断,其中REMem使用一个具有精心挑选工具的代理检索器,对记忆图进行迭代检索。在四个事件记忆基准测试中的全面评估显示,REMem在事件回忆和推理任务上分别比最先进的记忆系统Mem0和HippoRAG 2表现出3.4%和13.4%的绝对提升。此外,REMem还展示了对不可回答问题更稳健的拒绝行为。

英文摘要:

Humans excel at remembering concrete experiences along spatiotemporal contexts and performing reasoning across those events, i.e., the capacity for episodic memory. In contrast, memory in language agents remains mainly semantic, and current agents are not yet capable of effectively recollecting and reasoning over interaction histories. We identify and formalize the core challenges of episodic recollection and reasoning from this gap, and observe that existing work often overlooks episodicity, lacks explicit event modeling, or overemphasizes simple retrieval rather than complex reasoning. We present REMem, a two-phase framework for constructing and reasoning with episodic memory: 1) Offline indexing, where REMem converts experiences into a hybrid memory graph that flexibly links time-aware gists and facts. 2) Online inference, where REMem employs an agentic retriever with carefully curated tools for iterative retrieval over the memory graph. Comprehensive evaluation across four episodic memory benchmarks shows that REMem substantially outperforms state-of-the-art memory systems such as Mem0 and HippoRAG 2, showing 3.4% and 13.4% absolute improvements on episodic recollection and reasoning tasks, respectively. Moreover, REMem also demonstrates more robust refusal behavior for unanswerable questions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑