MemLens让大模型记忆更智能，能自动识别并保留高价值信息。
MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents
- 将记忆条目视为独立数据对象，按价值高低管理
- 支持交互式分析，可评估记忆贡献度并优化存储策略
- 适合需要长期记忆的AI助手开发者和研究者
近期，内存管理已成为基于大模型的智能体的关键基础设施，直接影响长时推理、个性化响应和知识复用。然而，现有大模型记忆系统多采用粗粒度（无价值感知）的方式，对用户与大模型的交互记录一视同仁，导致冗余且低效的记录长期滞留内存。为此，我们提出MemLens，一个价值感知的记忆管理系统，将记忆记录作为第一类数据对象。MemLens提供端到端的交互式分析仪表盘，展示完整的记忆生命周期，包括基于Shapley值的记忆评估、价值感知的存储机制以及记忆辅助的响应生成。通过一个学习协作者应用，系统使用户能够检查记忆价值、可视化层级记忆结构，并在响应质量、检索延迟和令牌消耗方面对比不同记忆管理策略。因此，MemLens可作为高效、可解释且个性化的长时记忆管理方案，适用于基于大模型的智能体。
原文摘要 · Abstract (English)
Recently, memory management has become a key infrastructure for LLM-based agents, as it directly affects long-horizon reasoning, personalized responses, and knowledge reuse. However, existing LLM memory systems typically adopt a coarse-grained (utility-agnostic) manner that treats heterogeneous user-LLM interaction records uniformly, leading to redundant and low-impact records persisting in the memory repository. To address this challenge, we present MemLens, a value-aware memory management system that takes memory records as first-class data objects. MemLens provides an end-to-end interactive analytics dashboard that exposes the complete memory lifecycle, including Shapley-style memory evaluation, value-aware storage, and memory-assisted response. Through a study-copilot application, the system enables users to inspect memory values, visualize hierarchical memory structures, and compare various memory management strategies in terms of response quality, retrieval latency, and token consumption. Therefore, our MemLens can serve as an efficient, interpretable, and personalized long-term memory management system for LLM-based agents.
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。