社会思维链：一种基于医学鉴别诊断方法论的多智能体架构
Social Chain of Thought: A Multi-Agent Architecture Grounded in Medical Differential Diagnosis Methodology
浏览论文内容
中文总结 AI 辅助
本文提出基于医学鉴别诊断方法论的多智能体架构SCoT，通过多轮专家协作提升复杂病例诊断召回率，其优势无法通过单一推理实现。
中文摘要 AI 辅助
医学诊断推理是大语言模型（LLM）的高影响力应用场景，对用户的健康与福祉具有重要意义。OpenAI（2026）报告显示，全球超过5%的ChatGPT消息与医疗相关，这类系统的透明度成为关键设计考量，尤其在复杂病例中，鉴别诊断往往需要整合多领域专家的推理形式。现有研究已提出多智能体医疗诊断方法，但仍不清楚这类系统的适用场景、帮助原因及相较于单一推理的优势所在。本文提出社会思维链（Social Chain of Thought，SCoT），这是一种用于医学鉴别诊断的多轮流程，将多智能体交互构建为协作式LLM推理的审议框架。通过将SCoT与单智能体基线、单智能体流程 ablation 实验及n-best缩放方法对比评估，结果表明其召回率优势无法仅通过单一推理实现；SCoT在最困难的诊断病例中表现最佳，多轮专家对话有助于恢复真实诊断并收敛至更高召回率的鉴别结果。
英文摘要
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.
