MedCache：面向纵向临床智能体的高效且具备时间有效性的记忆机制

中文摘要 AI 辅助

纵向临床智能体必须从分布在就诊、时间点和专科的证据中维护不断演变的患者状态，然而针对该场景应如何设计智能体记忆机制仍不明确。本文引入了多就诊、多专科患者记录基准，用于评估长上下文证据检索、跨时间证据聚合及跨专科临床推理。基于该基准，系统研究了四类记忆设计选择：整理、组织、检索及记忆增强推理。研究发现：时间有效性比单纯保留更多历史更重要；按专科分解的记忆可减少上下文但可能隐藏共享证据；当专科医生需共同推理而非仅证据来自多个记忆时，多智能体才会发挥作用。基于这些发现，本文提出了MedCache这一混合框架，该框架可构建具备时间有效性的患者记忆，将证据组织为重叠的专科视图，将每个查询路由至相关记忆，并自适应调用一个或多个专科医生。实验表明，MedCache相较于强大的单智能体和多智能体基线，提升了推理准确率和记忆效率，同时可在不同模型骨干及外部数据集上实现泛化。

英文摘要

Longitudinal clinical agents must maintain an evolving patient state from evidence distributed across visits, time points, and specialties. However, how agent memory should be designed for this setting remains unclear. We introduce a benchmark of multi-visit, multi-specialty patient records that evaluates long-context evidence retrieval, cross-time evidence aggregation, and cross-specialty clinical reasoning. Using this benchmark, we systematically study four memory design choices: curation, organization, retrieval, and memory-augmented reasoning. We find that temporal validity is more important than simply retaining more history; specialty-factorized memory reduces context but can hide shared evidence; and multiple agents help when specialists must reason together, not merely when evidence comes from multiple memories. Guided by these findings, we propose \textit{MedCache}, a hybrid framework that constructs temporally valid patient memory, organizes evidence into overlapping specialty views, routes each query to relevant memories, and adaptively invokes one or multiple specialists. Experiments show that MedCache improves reasoning accuracy and memory efficiency over strong single-agent and multi-agent baselines, while generalizing across model backbones and external datasets.

发表机构

• University of Michigan（密歇根大学）

机构由 AI 辅助整理，请以论文原文为准。