arXiv cs.AI· Shangze Li, Yanyu Yao, Derong Xu, Zhi Zheng, Tong Xu·· 12 小时前AI 评分34
MemCompile：面向长期智能体记忆的查询条件化证据编译框架
From Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent Memory
AI 导读
MemCompile 是一个查询条件化的证据编译框架，用于长期对话记忆：Address Plane 通过紧凑的源链接描述符和容量感知 Cells 定位相关支撑，Evidence Plane 则在有限证据预算内将保留的论断渲染为可直接作答的上下文。
正文 · 原文
Abstract:Long-term agent memory requires recovering answer-relevant evidence dispersed across turns and sessions. Existing systems increasingly use structured memories and adaptive retrieval, yet often pass retrieved or expanded units directly to the reader, coupling memory addressing with evidence presentation and leaving the final context redundant or incomplete. To address this gap, we propose MemCompile, a query-conditioned evidence compilation framework for long-term conversational memory. Given a query, the Address Plane locates relevant support through compact source-linked descriptors and capacity-aware Cells, while a normalization boundary resolves heterogeneous retrieval hits to stable SourcePacket identities. Its Evidence Plane then allocates a bounded evidence budget across complementary packets, admits limited additional support, and renders the retained claims associated with each selected packet into an answer-ready context. MemCompile achieves 80.52% Judge Accuracy on LoCoMo and extends the empirical quality-cost Pareto frontier to a higher-quality regime. Its strong performance on LongMemEval-S further suggests that the benefits of query-conditioned compilation generalize across long-term conversational-memory benchmarks.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.23313 [cs.AI] |
| (or arXiv:2610.23313v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23313 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shangze Li [view email]
[v1]
Fri, 16 Oct 2026 11:15:29 UTC (1,163 KB)
来源：arXiv cs.AI · arxiv.org