用智能体共进化模拟标准化病人，提升医患对话训练效果
LLMs Can Simulate Standardized Patients via Agent Coevolution
- 患者与医生智能体通过多轮对话互训，自主生成真实病人回应
- 在200例病例上进化10小时后，需求匹配度提升超10%，更受真人偏好
- 无需人工标注，适合医学教育与临床训练场景
基于大语言模型的标准化病人（SP）训练仍面临挑战，需专业领域知识与角色化实践。现有研究多聚焦于提升数据检索准确率或通过人工反馈调整提示词，却忽视了患者智能体需通过无监督仿真学习标准化表达模式，将信息转化为类人化回应的关键能力。为此，我们提出EvoPatient框架，患者智能体与医生智能体通过多轮对话共同模拟诊疗过程，同步积累经验以优化提问与回答质量，最终实现对人类医生的有效训练。在多种病例上的实验证明，仅提供总体SP要求，该框架在需求匹配度上优于现有推理方法超过10%，且更符合人类偏好；经过200例案例、10小时演化后，达到资源消耗与性能的最优平衡，并展现出优异泛化能力。系统代码已开源：https://github.com/ZJUMAI/EvoPatient。
原文摘要 · Abstract (English)
Training medical personnel using standardized patients (SPs) remains a complex challenge, requiring extensive domain expertise and role-specific practice. Previous research on Large Language Model (LLM)-based SPs mostly focuses on improving data retrieval accuracy or adjusting prompts through human feedback. However, this focus has overlooked the critical need for patient agents to learn a standardized presentation pattern that transforms data into human-like patient responses through unsupervised simulations. To address this gap, we propose EvoPatient, a novel simulated patient framework in which a patient agent and doctor agents simulate the diagnostic process through multi-turn dialogues, simultaneously gathering experience to improve the quality of both questions and answers, ultimately enabling human doctor training. Extensive experiments on various cases demonstrate that, by providing only overall SP requirements, our framework improves over existing reasoning methods by more than 10\% in requirement alignment and better human preference, while achieving an optimal balance of resource consumption after evolving over 200 cases for 10 hours, with excellent generalizability. Our system will be available at https://github.com/ZJUMAI/EvoPatient.
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。