先测量再管理：评估编码智能体的工作记忆

中文摘要 AI 辅助

智能体的工作记忆具有异质性，指令、工件、工具输出以及智能体生成的状态等对象扮演着不同的语义角色，且呈现出不同的规模、保留和表征特性。近期研究已开始探索能应对这种异质性的记忆管理机制，本研究聚焦于语义异质性，探讨其应如何塑造编码智能体工作记忆的管理与评估。在55条已归档的编码智能体轨迹中，我们发现语义不同的工作记忆对象呈现出 distinct 的保留和压缩行为，这种异质性促使采用语义感知的记忆管理。我们研究了两种语义感知策略：对象感知压缩策略和基于检索的策略。评估显示，校准增益可能无法迁移到未见过的任务，相同的token预算并不意味着相同的交付上下文或管理成本，真实系统回放进一步暴露了仅靠名义预算无法捕捉的服务限制。这些结果共同表明，语义结构对智能体工作记忆的重要性，以及评估记忆管理策略需要的不只是名义token预算。我们将这些经验整理为四个层面：存储状态、交付上下文、管理工作以及任务或过程结果。

英文摘要

Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles and exhibit different size, retention, and representation profiles. Recent work has begun to explore memory-management mechanisms that account for such heterogeneity. This work focuses on semantic heterogeneity and studies how it should shape the management and evaluation of working memory in coding agents. Across 55 archived coding-agent trajectories, we find that semantically different working-memory objects exhibit distinct retention and compression behavior. This heterogeneity motivates semantically informed memory management. We study two semantically informed strategies: an object-aware compression policy and a retrieval-based policy. Their evaluation shows that calibration gains may not transfer to held-out tasks, and that equal token budgets do not imply equal delivered context or management cost. A real-system replay further exposes serving limits that nominal budgets alone do not capture. Together, these results show why semantic structure matters for agent working memory and why evaluating memory-management strategies requires more than a nominal token budget. We organize these lessons into four levels: stored state, delivered context, management work, and task or process outcome.

发表机构

• Argonne National Laboratory（阿贡国家实验室）
• Columbia University（哥伦比亚大学）
• University of Houston（休斯顿大学）

机构由 AI 辅助整理，请以论文原文为准。