用大模型智能精简长期记忆，既省空间又不丢关键信息
MemRefine: LLM-Guided Compression for Long-Term Agent Memory
- 让大模型判断哪些记忆该删、该合、该留，而非只看表面相似度
- 在多个基准上达成目标存储预算，且下游任务性能不下降
- 特别适合内存受限设备，如手机或嵌入式系统使用
大型语言模型（LLM）代理在长期交互中需持续保留并调用过往对话信息。但随着交互累积，记忆库无限膨胀，冗余内容增多，导致存储成本上升、检索效率下降。尤其在内存受限平台，这一问题更为严峻。为此，本文提出MemRefine框架，突破传统基于表面相似度的压缩方式，利用相似度仅生成候选对，再由一个大模型裁判根据事实内容判断删除、合并或保留，迭代直至满足固定存储预算。在多个记忆框架与长期对话基准上，MemRefine始终达到目标预算，同时保持下游任务性能，优于基于规则的基线方法，尤其在严格预算下表现更优。
原文摘要 · Abstract (English)
Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and recalled to support future tasks. However, as interactions accumulate, the memory store grows without bound and fills with redundant entries that inflate storage cost and degrade retrieval by crowding out the most useful evidence. Furthermore, this is especially limiting on resource-constrained platforms with hard memory budgets, motivating us to formulate storage-budgeted memory management, the task of keeping an already constructed memory store within a fixed budget while preserving information useful for future interactions. To this end, we then propose MemRefine, an LLM-guided framework that, since surface similarity poorly reflects factual value, uses similarity only to propose candidate pairs and defers delete, merge, and preserve decisions to an LLM judge based on factual content, iterating until the budget is met. Across multiple memory frameworks and long-term conversation benchmarks, MemRefine consistently meets target budgets while preserving downstream performance and outperforming rule-based baselines under tight budgets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。