ETAMem：为长期对话智能体解耦并对齐异构记忆

View PDF HTML (experimental)

Abstract:Long-term memory enables Large Language Models (LLMs) to maintain coherent and personalized interactions across extended conversations. However, existing memory systems face two key challenges: (1) Information Entanglement, where heterogeneous information is mixed within coarse-grained memory units; and (2) Organizational Mismatch, where memory structures based primarily on semantic similarity may overlook other associations. To address these challenges, we propose ETAMem, a multi-view memory framework that decouples heterogeneous conversational information and aligns memory representations and organization with its distinct characteristics. Specifically, heterogeneous information parsing extracts atomic memory units and identifies affective information. View-specific memory structuring then organizes these units into three complementary hierarchical views: Event, Affect, and Time. ETAMem incrementally maintains memory structures with adaptively calibrated thresholds. For retrieval, entropy-based retrieval allocates query-specific budgets across views and performs hierarchical search within each view. Experiments on LoCoMo and LongMemEval-S demonstrate that ETAMem outperforms state-of-the-art baselines, achieving relative accuracy improvements of 12.46% and 7.96%, respectively, while maintaining competitive token efficiency. Further analyses demonstrate the complementary benefits of different memory views.

Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2610.37443 [cs.CL]
	(or arXiv:2610.37443v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.37443 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xinying Qian [view email]
[v1] Tue, 27 Oct 2026 15:51:42 UTC (5,959 KB)