摘要
大型语言模型虽在医学知识评估中表现优异，但在不确定性下的临床推理需主动决策调查内容。本研究构建血液肿瘤学代理评估框架，要求模型在三轮交互中主动请求数据以制定诊疗方案。结果显示，最佳模型准确率仅 68%，信息利用率是预测准确性的最强指标，但在末轮显著下降。推理轨迹虽逻辑连贯却与准确性脱节，主要失败模式为搜索满足、锚定效应及过早闭合，揭示了当前模型在不确定性下信息寻求的系统性缺陷。
AI 推荐理由
论文核心研究临床推理中的信息寻求失败，深入分析认知偏差与推理轨迹。
研究机构
Technical University of Munich, School of Medicine and Health, TUM University Hospital, Klinikum rechts der Isar, Department of Medicine III, Munich, Germany
Department of Hematology, Oncology and Cancer Immunology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
German Cancer Research Center (DKFZ), Heidelberg, Germany
Department of Medicine III, LMU University Hospital, Munich, Germany
Department of Medicine A, Hematology/Oncology, University Hospital Münster, Münster, Germany
Oncology/Hematology im Elsendorf, Munich, Germany
Department of Hematology, Oncology and Palliative Care, Klinikum Traunstein, Traunstein, Germany
论文信息