← 研踪 PaperTrailarXiv:2610.39790 · v1
Long-Term Agent Memory through Complementary Curation and Consolidation
首次提交 2026-10-29 18:40
版本更新 2026-10-29 18:40
雷达观测 2026-10-30 13:28
摘要
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.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-10-29 18:40 · 最新观测版本
Long-Term Agent Memory through Complementary Curation and Consolidation
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.
查看此版本解读 →查看此版本原文 ↗