用操作痕迹自动评估记忆价值，让大模型学会高效管理长期记忆。
Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit
- 通过检索命中和引用记录，离线训练记忆效用评判器。
- 在线生成时，仅用一次删除重答即可计算记忆存在奖励，无需人工标注。
- 在长程任务上超越现有方法，适合需要持久记忆的智能体研究者。
长周期大模型智能体的记忆操作难以监督：操作发生时其价值不可见。但这类操作会留下可机器读取的轨迹证据——检索命中与回答时刻的引用。本文提出Hindsight Memory-PRM，两次利用这一审计线索：离线训练一个基于操作条件的记忆效用评判器；在线阶段，通过检索、引用及单次受控的删除-重答过程，确定干预校准的初始存在信用，并沿版本链传播作为动作级代理奖励——无需逐操作人工标注，也无需蒙特卡洛式延续重演。在独立测试集LoCoMo上，80亿参数策略模型在固定共享阅读器下达到77.5%，超过其API教师（65.1%）及所有复现的外部系统，仅需Mem0官方操作点八分之一的上下文；在LongMemEval上达79.0%。消融实验表明增益源于因果校准而非信号密度，且策略收敛至多版本记忆组织结构，此优势为所有测试的开环基线无法复现。
原文摘要 · Abstract (English)
Memory operations of long-horizon LLM agents are hard to supervise: an operation's value is unobservable when it is taken. But they are special -- they leave machine-readable evidence in the trajectory: retrieval hits and answer-time citations. Hindsight Memory-PRM exploits this audit trail twice: offline to train an operation-conditioned memory-utility critic, and online, where retrievals, citations, and one controlled deletion-and-reanswer per probe settle an intervention-calibrated entry-level presence credit, propagated along version chains as an action-level proxy reward -- no per-operation human labels, no Monte-Carlo replay of continuations. On held-out LoCoMo a local 8B policy reaches 77.5% under a fixed shared reader, surpassing its API teacher (65.1%) and all reproduced external systems, at one eighth the context of Mem0's official operating point; on LongMemEval, 79.0%. Ablations attribute the gain to causal calibration rather than signal density, and the policy converges to a multi-version memory organization whose gains no tested open-loop baseline reproduces.
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。