发表机构
University of California, Los Angeles; Optum AI, UnitedHealth Group（加州大学洛杉矶分校; Optum AI，联合健康集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对临床智能体记忆管理，提出状态转移感知框架STAM，通过语义检索与类型化关系区分当前与历史信息，在四个纵向基准上验证其有效性。
AI 中文摘要
在临床记录上进行推理的大型语言模型（LLM）智能体必须跟踪患者状态的变化，同时保留理解这些变化所需的历史信息。简单地累积记忆会让人不清楚哪些信息仍然适用，而覆盖早期记忆则可能抹去重建治疗历史和临床轨迹所需的证据。我们引入了STAM，一种状态转移感知的记忆框架，它在新临床条目到达时记录状态变化。STAM将语义检索与类型化临床关系相结合，以识别受影响的记忆，将当前信息保存在Active中，将已取代或已解决的信息保存在History中。在读取时，一个查询相关的门控会选择性地提供历史记忆。在四个纵向临床基准上，我们使用下游问答、直接状态维护诊断以及在大致匹配的上下文长度下的比较来评估STAM。
英文摘要
Large language model (LLM) agents that reason over clinical records must track changes in a patient's state while preserving the history needed to understand them. Simply accumulating memories leaves it unclear which information still applies, whereas overwriting earlier memories can erase evidence needed to reconstruct treatment history and clinical trajectories. We introduce STAM, a state-transition-aware memory framework that records state changes as new clinical entries arrive. STAM combines semantic retrieval with typed clinical relations to identify affected memories, maintaining current information in Active and superseded or resolved information in History. At read time, a query-dependent gate selectively serves historical memory. Across four longitudinal clinical benchmarks, we evaluate STAM with downstream question answering, direct state-maintenance diagnostics, and comparisons at approximately matched context lengths.
