发表机构
South China University of Technology; Hong Kong Polytechnic University; Guangzhou University; Guangxi University; King’s College London（华南理工大学; 香港理工大学; 广州大学; 广西大学; 伦敦国王学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对LLM用于医疗转诊的信息过载与非结构化协作问题，提出MASGR框架，通过多智能体结构化图推理及专家仲裁机制提升复杂医疗转诊的精准度，表现优于现有模型。
AI 中文摘要
医疗转诊（即引导患者前往合适的医院科室）是一项复杂的决策过程，需要整合多模态数据，包括患者叙述、实验室指标及放射影像。尽管大型语言模型（LLM）已推动医疗对话系统发展，但在现实转诊任务中仍存在两大核心局限：（1）信息过载：模型过度关注高频疾病术语，却忽略微妙但关键的紧急指标；（2）非结构化协作：现有多智能体框架依赖松散对话，导致语义漂移与确认偏差。为应对这些挑战，我们提出MASGR（多智能体结构化图推理）框架，将转诊任务从分类问题转化为结构化图构建问题。MASGR部署专用智能体从不同模态提取证据，并通过临床推理图协调各智能体，该图强制智能体在冲突证据间建立明确逻辑关联。此外，我们整合知识引导的仲裁机制，将患者安全规则置于标准诊断分类之上。对真实医疗记录的大量实验表明，MASGR显著优于最先进的LLM及现有多智能体系统，尤其在需平衡慢性病管理与紧急干预的复杂病例中表现突出。本研究的AI贡献在于MASGR框架，它将非结构化多智能体对话转化为可验证的逻辑图构建；工程应用则通过其在复杂医疗决策系统中的部署，优化了复杂医疗转诊的精准度。
英文摘要
Medical referral (directing patients to the appropriate hospital department) is a complex decision-making process requiring the synthesis of multimodal data, including patient narratives, laboratory indicators, and radiology imaging. While Large Language Models (LLMs) have advanced medical dialogue systems, they struggle with real-world referral tasks due to two primary limitations: (1) Information Overload, where models fixate on high-frequency disease terms while overlooking subtle but critical urgency indicators; and (2) Unstructured Collaboration, where existing multi-agent frameworks rely on loose dialogue that leads to semantic drift and confirmation bias. To address these challenges, we introduce MASGR (Multi-Agent Structured Graph Reasoning), a framework that treats referral not as a classification task but as a structured graph construction problem. MASGR deploys specialized agents to extract evidence from distinct modalities and coordinates them through a clinical reasoning graph. This graph forces agents to establish explicit logical connections between conflicting evidence. Furthermore, we integrate a knowledge-guided arbitration mechanism that prioritizes patient safety rules over standard diagnostic classification. Extensive experiments on real-world medical records demonstrate that MASGR significantly outperforms state-of-the-art LLMs and existing multi-agent systems, particularly in complex cases requiring the balancing of chronic disease management and emergency intervention. The AI contribution lies in the Multi-Agent Structured Graph Reasoning framework that transforms unstructured multi-agent dialogue into a verifiable logical graph construction. The engineering application is demonstrated through its deployment in a complex healthcare decision-making system to optimize the precision of complex medical referrals.
Comments18 pages
