用多智能体协作模拟医生会诊，提升复杂病案诊断准确率
Social Chain of Thought: A Multi-Agent Architecture Grounded in Medical Differential Diagnosis Methodology
- 设计多轮协作框架，让不同角色智能体像医生会诊般讨论诊断
- 在最难病例中召回率显著提升，比单模型推理高出17%
- 适合需要多专家协同的复杂医疗决策场景
医学诊断是大语言模型的重要应用，关乎用户健康。当全球超过5%的ChatGPT消息涉及医疗时，系统透明性成为关键挑战。尤其在复杂病例中，鉴别诊断需整合多种专科推理。现有方法虽提出多智能体架构，但其必要性、有效性及优势边界仍不明确。本文提出社会性思维链（SCoT），一种基于医学鉴别诊断方法的多轮协作流程，将多智能体交互结构化为协同推理框架。在与单智能体基线、单轮流程消融实验及best-of-n扩展对比中，证明其召回率优势无法由单体推理复制。SCoT在最困难的诊断案例中表现最优，多轮专业对话有助于恢复真实诊断并提高鉴别诊断覆盖率。
原文摘要 · Abstract (English)
Medical diagnostic reasoning is a high-impact use case for LLMs that carries significant implications for the health and wellbeing of users. When OpenAI (2026) reports that more than 5% of ChatGPT messages globally are healthcare-related, the transparency of these systems becomes a serious design concern. This is especially true for complex cases, where differential diagnosis often requires integrating multiple forms of specialist reasoning. Existing work has proposed multi-agent approaches to medical diagnosis, but it remains unclear when such systems are needed, why they help, and where they outperform monolithic inference. We introduce Social Chain of Thought (SCoT),a multi-round pipeline for medical differential diagnosis that structures multi-agent interaction as a deliberative framework for collabora. tive LLM reasoning. Evaluating SCoT against single-agent baselines, one-agent pipeline ablations, and best-of-n scaling, we show that its recall advantage is not reproduced by monolithic inference alone. SCoT is most successful in the hardest diagnostic cases, where multiple rounds of specialist conversation help recover ground-truth diagnoses and converge on a higher-recall differential.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。