arXiv cs.AI· Abhishek Gupta, Dongge Han, Daniel Madrigal Diaz, Wei-Ning Chen, Mayukh Das, Victor R\"uhle, Saravan Rajmohan·· 2 小时前AI 评分42
通过互补的整理与整合机制实现长期 Agent 记忆
Long-Term Agent Memory through Complementary Curation and Consolidation
AI 导读
arXiv 论文提出一种混合记忆架构，结合情景记忆与结构化关系记忆，并配套整合机制以保持效率。在 LoCoMo 和 LongMemEval-S 两个基准上的实验显示，两类记忆持续互补，组合使用超越 SOTA 记忆框架，分别取得 90.2% 和 85.5% 的准确率。
正文 · 原文
Abstract:Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising episodic memories and structured relational memories and a consolidation mechanism which preserves efficiency. We conduct an empirical study across two benchmarks: LoCoMo and LongMemEval-S. Our experiments demonstrate that the two memory types are consistently complementary, combining both outperform state-of-the-art memory frameworks and achieves 90.2% accuracy on LoCoMo and 85.5% on LongMemEval-S.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.39790 [cs.AI] |
| (or arXiv:2610.39790v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.39790 arXiv-issued DOI via DataCite |
Submission history
From: Abhishek Gupta [view email]
[v1]
Thu, 29 Oct 2026 10:40:18 UTC (603 KB)
来源：arXiv cs.AI · arxiv.org