用多智能体协作让AI能像医生一样规范问诊精神疾病。
MAGI: Multi-Agent Guided Interview for Psychiatric Assessment
- 四类智能体分工合作，按诊断流程动态引导问诊。
- 在1002名患者上测试，诊断准确率显著优于传统LLM方法。
- 生成可解释的推理链，适合临床验证和医生信任使用。
自动化结构化临床访谈有望提升精神健康医疗可及性，但现有大语言模型方法难以契合精神科诊断规范。我们提出MAGI，首个将金标准《迷你国际神经精神访谈》（MINI）转化为自动计算流程的多智能体框架。MAGI通过四个专业化智能体协同工作：1）遵循MINI分支结构的导航智能体；2）融合诊断探查、解释与共情的自适应提问智能体；3）验证用户回答是否满足节点条件的判断智能体；4）生成心理量表思维链（PsyCoT）的诊断智能体，明确映射症状与临床标准。在覆盖抑郁、广泛性焦虑、社交焦虑及自杀风险的1002名真实参与者上测试显示，MAGI通过结合临床严谨性、对话适应性和可解释推理，显著提升LLM辅助精神健康评估效果。
原文摘要 · Abstract (English)
Automating structured clinical interviews could revolutionize mental healthcare accessibility, yet existing large language models (LLMs) approaches fail to align with psychiatric diagnostic protocols. We present MAGI, the first framework that transforms the gold-standard Mini International Neuropsychiatric Interview (MINI) into automatic computational workflows through coordinated multi-agent collaboration. MAGI dynamically navigates clinical logic via four specialized agents: 1) an interview tree guided navigation agent adhering to the MINI's branching structure, 2) an adaptive question agent blending diagnostic probing, explaining, and empathy, 3) a judgment agent validating whether the response from participants meet the node, and 4) a diagnosis Agent generating Psychometric Chain-of- Thought (PsyCoT) traces that explicitly map symptoms to clinical criteria. Experimental results on 1,002 real-world participants covering depression, generalized anxiety, social anxiety and suicide shows that MAGI advances LLM- assisted mental health assessment by combining clinical rigor, conversational adaptability, and explainable reasoning.
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。