用多智能体框架让医疗会诊模型持续进化，提升诊断准确率。
MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation
- 设计多智能体协作机制，通过共识聚合与残差讨论减少冗长对话。
- 构建正确答案与思维链知识库，在测试集上达90.1%和83.9%准确率。
- 支持错误反思与经验积累，适合需要持续优化的医疗AI系统。
大型语言模型在多个领域取得进展，但在多学科团队（MDT）医疗会诊中仍面临挑战。现有方法通过角色分配、任务分解和积累医疗经验来增强推理能力，但多角色协作常导致对话历史过长，增加模型认知负担，降低效率与准确性。部分方法仅存储治疗记录，未提取有效经验或反思错误，限制了知识泛化与系统演化。本文提出基于LLM的多智能体MDT医疗会诊框架，采用共识聚合与残差讨论结构实现多轮协作，并建立正确答案知识库（CorrectKB）与思维链知识库（ChainKB）以积累会诊经验。该机制使系统可自我演进，持续提升诊断合理性与准确性。在MedQA和PubMedQA数据集上的实验表明，框架分别达到90.1%和83.9%的准确率，且构建的知识库在两个数据集的测试集上均表现出良好泛化能力。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have made significant progress in various fields. However, challenges remain in Multi-Disciplinary Team (MDT) medical consultations. Current research enhances reasoning through role assignment, task decomposition, and accumulation of medical experience. Multi-role collaboration in MDT consultations often results in excessively long dialogue histories. This increases the model's cognitive burden and degrades both efficiency and accuracy. Some methods only store treatment histories. They do not extract effective experience or reflect on errors. This limits knowledge generalization and system evolution. We propose a multi-agent MDT medical consultation framework based on LLMs to address these issues. Our framework uses consensus aggregation and a residual discussion structure for multi-round consultations. It also employs a Correct Answer Knowledge Base (CorrectKB) and a Chain-of-Thought Knowledge Base (ChainKB) to accumulate consultation experience. These mechanisms enable the framework to evolve and continually improve diagnosis rationality and accuracy. Experimental results on the MedQA and PubMedQA datasets demonstrate that our framework achieves accuracies of 90.1% and 83.9%, respectively, and that the constructed knowledge bases generalize effectively across test sets from both datasets.
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。