Search papers, labs, and topics across Lattice.
This paper introduces Social Chain of Thought (SCoT), a multi-agent architecture designed to enhance medical differential diagnosis by facilitating collaborative reasoning among specialists. The study evaluates SCoT against traditional single-agent models and various ablation studies, revealing that SCoT significantly improves recall, particularly in complex diagnostic scenarios. The findings underscore the importance of multi-agent interactions in achieving higher accuracy in challenging medical cases, highlighting a clear advantage over monolithic inference methods.
Multi-agent collaboration in medical diagnosis can dramatically improve recall rates, especially in complex cases where traditional models falter.
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.
