AgentEHR：基于回顾性摘要推演的自主动态临床决策系统

摘要

大型语言模型在医疗领域已展现出深远应用价值，然而其在自主电子健康记录导航方面的应用仍受限于对人工筛选输入的依赖及简化检索任务。为弥合理想化实验场景与真实临床环境之间的差距，我们提出AgentEHR基准测试框架。该框架要求智能体在原始高噪声数据库中执行诊断与治疗方案制定等复杂决策任务，需进行长程交互推理。在应对这些任务时，我们发现现有摘要方法必然面临关键信息丢失与推理连续性断裂的局限。为此，我们提出RetroSum创新框架，将回溯摘要机制与动态经验策略相融合。通过动态重估交互历史，回溯机制可防止长上下文信息丢失并确保逻辑连贯性。同时，动态经验策略通过从记忆库检索累积经验来弥合领域差距。大量实证评估表明，RetroSum相较基线模型最高可实现29.16%的性能提升，同时将总体交互错误率显著降低92.3%。

English

Large Language Models have demonstrated profound utility in the medical domain. However, their application to autonomous Electronic Health Records~(EHRs) navigation remains constrained by a reliance on curated inputs and simplified retrieval tasks. To bridge the gap between idealized experimental settings and realistic clinical environments, we present AgentEHR. This benchmark challenges agents to execute complex decision-making tasks, such as diagnosis and treatment planning, requiring long-range interactive reasoning directly within raw and high-noise databases. In tackling these tasks, we identify that existing summarization methods inevitably suffer from critical information loss and fractured reasoning continuity. To address this, we propose RetroSum, a novel framework that unifies a retrospective summarization mechanism with an evolving experience strategy. By dynamically re-evaluating interaction history, the retrospective mechanism prevents long-context information loss and ensures unbroken logical coherence. Additionally, the evolving strategy bridges the domain gap by retrieving accumulated experience from a memory bank. Extensive empirical evaluations demonstrate that RetroSum achieves performance gains of up to 29.16% over competitive baselines, while significantly decreasing total interaction errors by up to 92.3%.

AgentEHR：基于回顾性摘要推演的自主动态临床决策系统

AgentEHR: Advancing Autonomous Clinical Decision-Making via Retrospective Summarization

摘要

Support