用注意力机制指导记忆更新，让智能体更精准修正错误记忆。
Mechanistic Attention Guidance for Agent Memory Refinement
- 通过注意力分析记忆片段使用情况，发现利用模式
- 在交互决策任务中提升性能与记忆效率
- 适合需要可靠记忆修正的自主智能体系统
现有自进化记忆系统主要基于文本输出（如任务轨迹和反思）优化记忆，但缺乏对内部机制信号的利用，导致记忆调用方式不透明，易引发错误归因与虚构记忆。本文发现，检索头注意力能揭示记忆片段在决策过程中的段级使用情况。通过聚合注意力生成上下文利用率矩阵，可识别重复的记忆使用模式，并指导针对性改进策略。基于此提出注意力引导的记忆精炼框架（AGMR），针对失败执行修正或增强记忆，成功执行则简化记忆，并通过重执行验证每项更新。在交互决策基准测试中，AGMR显著优于仅依赖文本的基线方法，在任务表现与记忆效率上均有提升。
原文摘要 · Abstract (English)
Existing self-evolving memory systems mainly improve agent memory based on textual outputs, such as task trajectories and reflections. However, this text-based paradigm rarely incorporates internal mechanistic signals, leaving how retrieved memory is actually utilized during task execution underexplored. This limitation can lead to unreliable error attribution and hallucinated memory modifications. In this work, we show that retrieval-head attention provides a mechanistic signal for revealing segment-level memory utilization. By aggregating attention over memory segments and decision steps, we construct a context utilization matrix that exposes recurring memory-use patterns and indicates corresponding refinement strategies. Building on this observation, we propose Attention-Guided Memory Refinement (AGMR), a framework that uses utilization patterns revealed by attention to guide targeted segment-level memory updates. AGMR corrects or enhances memory for failed executions, simplifies memory for successful executions, and verifies each update through re-execution. Experiments on interactive decision-making benchmarks show that AGMR improves both task performance and memory efficiency over text-only memory refinement baselines. Code is available at https://anonymous.4open.science/r/AGMR_code-3262/
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。