arXiv cs.AI· Qiyuan Li, Xiaomei Guo, Chao Gao, Haijiang Liu, Deyu Chen, Caicai Guo, Jinguang Gu·· 3 小时前AI 评分37
CoRPS-Dial：双智能体框架解耦患者画像与临床流程，生成逼真医疗对话
Decoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation
AI 导读
研究者提出 CoRPS-Dial，一个可控的双智能体医疗对话合成框架，通过画像驱动的患者智能体与遵循临床指南流程的医生智能体交互生成预问诊对话，并进行角色一致性、流程完整性和文本一致性的质量控制。在冠心病场景的实验显示，合成对话在信息覆盖、临床合规性和自然度上更接近真实对话，下游微调也验证了数据的实用价值。
正文 · 原文
Abstract:Pre-consultation medical dialogues are essential for collecting comprehensive patient information, but are costly to obtain at scale due to privacy and ethical constraints. Existing LLM-based synthesis methods often rely on prompt engineering or rigid rules, limiting their ability to balance clinical relevance with realistic patient diversity. We propose CoRPS-Dial, a controllable dual-agent framework for pre-consultation medical dialogue synthesis that integrates patient personas with guideline-aligned clinical workflow rules. CoRPS-Dial generates dialogues through interactions between a persona-driven patient agent and a process-guided doctor agent, followed by post-hoc quality control for role consistency, workflow completeness, and textual consistency. Experiments on coronary heart disease demonstrate that CoRPS-Dial improves alignment between synthetic and real dialogues in information coverage, clinical compliance, and dialogue naturalness. Downstream fine-tuning experiments further confirm the utility of the generated synthetic data for medical dialogue tasks. These results highlight the effectiveness of CoRPS-Dial for clinically grounded and controllable medical dialogue synthesis.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.32443 [cs.CL] |
| (or arXiv:2610.32443v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32443 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haijiang Liu [view email]
[v1]
Fri, 23 Oct 2026 10:07:35 UTC (696 KB)
来源：arXiv cs.AI · arxiv.org