Debate-Mixture-of-Agents (DMoA), a novel multi-agent framework that structures role-based interaction to support iterative diagnostic reasoning, is developed and demonstrated the potential of DMoA for clinical tasks and suggests further investigation of multi-agent frameworks.
Abstract
Large language models (LLMs) show potential for medical tasks, but their single-turn question-answer format does not reflect how clinical diagnosis is performed in practice. As a result, they remain limited in complex diagnostic settings. We developed Debate-Mixture-of-Agents (DMoA), a novel multi-agent framework that structures role-based interaction to support iterative diagnostic reasoning. Base models and DMoA were evaluated on 297 rare disease cases and 1,719 challenging cases. Across both datasets, DMoA improved most likely diagnosis accuracy by 10.21 percentage points and safety rate by 11.36 percentage points over GPT-4o baseline. Ablation experiments showed that the gains were not simply due to the use of more models or longer outputs, but also reflected the contribution of the structured workflow. Further analyses examined how framework design, base model choice, and token budget affected performance. DMoA performed better with a 4*2 structure, stronger base models, and a larger token budget. These findings demonstrate the potential of DMoA for clinical tasks and suggest further investigation of multi-agent frameworks.
Large language models such as GPT-4, Med-PaLM 2, and BioMedLM are being increasingly applied to clinical decision support tasks including diagnostic reasoning, clinical documentation, medical question answering, and patient-facing health communication, with several studies reporting performance comparable to trained cl...
M. Oloko-Oba, Ebenezer Esenogho, Kehinde D. Aruleba et al.· Applied Informatics· 0 citations
The reported experiments characterize CLEAR-Med's configuration and scalability and the Invocation Agent's accuracy, while the formal analysis establishes the encoded-property guarantee of the complete control flow.
Erfan D. Dehkalani, S. Shankaran, Abbot R. Laptook et al.· 0 citations
Although Large Language Models (LLMs) have demonstrated potential in clinical documentation, generating the rigorous, evidence-based reasoning required for unprecedented, atypical, and rare disease case reports remains a significant challenge. We present MedCaseAgent, an end-to-end agentic reasoning paradigm that bridg...
Hong-Kang Chu, Yi-Fan Shen, Tianjiao Yu et al.· 0 citations
Large language models (LLMs) can generate differential diagnoses for complex cases, but a useful second opinion must also be factually grounded, clinically coherent, actionable, and safe. We developed a multidimensional benchmark using 300 diagnostically resolved NEJM--MedQA cases: 110 for physician reference ratings a...
A. Bokov, I. Panin, N. Nechaev et al.· 0 citations
Continuous physiological monitoring is central to emergency care, yet building trustworthy, clinically usable AI remains challenging. While LLMs translate complex physiological signals into natural-language clinical narratives, it remains unclear whether agentic reasoning frameworks improve the quality of explanations...
Davide Gabrielli, Paola Velardi, Stefano Faralli et al.· Proceedings of the 35th ACM...· 0 citations
Large language models (LLMs) have shown considerable promise in clinical decision support. However, existing approaches often rely on multi-step reasoning or multi-agent collaboration to execute clinical guidelines, introducing substantial computational overhead without reliably preventing decision errors. To address t...
Xiao-Qian Lu, Guang-Fu Guo, Long Cheng et al.· 0 citations