跳到正文
arXiv cs.AI· Jingyao Cai, Shuaijun Liu, Xiaowan Li, Yutong Guo, Abdul Rehman, Qintian, Thomas Dolby, Sue M Green, Xiaosong Yang·· 4 小时前AI 评分34

CPM-MultiAgent:基于 CPM 理论的多智能体框架,模拟医疗对话中患者情绪动态演化

CPM-MultiAgent: A CPM-Grounded Appraisal Framework for Simulating Dynamic Patient Emotional Evolution in Healthcare Dialogue

AI 导读

研究者提出 CPM-MultiAgent,一个以 Component Process Model(CPM)心理理论为基础的多智能体框架,用于医疗沟通训练中的患者情绪动态模拟。

正文 · 原文

View PDF HTML (experimental)

Abstract:Large Language Models (LLMs) enable patient simulation for healthcare communication training, where learners practice responding to clinical information, concerns, and emotional reactions. However, existing patient simulation and affective dialogue systems often represent patient emotions as static attributes or focus on recognizing emotions and generating empathetic responses. They provide limited support for modeling how a simulated patient's emotional state evolves in response to a healthcare professional's communication. Changes in patient emotion constitute interactional feedback that learners must recognize and respond to across dialogue turns. We draw on the Component Process Model (CPM), a psychological theory that explains emotion as a dynamic process shaped by event appraisal. We propose CPM-MultiAgent, a CPM-grounded multi-agent framework for dynamic patient emotion simulation in healthcare communication training. The framework uses an emotion taxonomy informed by medical literature and expert input, and updates emotional states through healthcare-related trigger identification, structured CPM appraisal, and emotion-state integration, accounting for the patient's profile, clinical context, and prior emotional state. We evaluate the framework through student-led conversations and controlled trigger cases, combining nursing-expert assessments, LLM-judge comparisons, component ablations, backbone checks, and student feedback.
Subjects: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
Cite as: arXiv:2607.07824 [cs.MA]
  (or arXiv:2607.07824v2 [cs.MA] for this version)
  https://doi.org/10.48550/arXiv.2607.07824

arXiv-issued DOI via DataCite

Submission history

From: Jingyao Cai [view email]
[v1] Wed, 8 Jul 2026 18:06:03 UTC (1,399 KB)
[v2] Fri, 13 Nov 2026 13:44:41 UTC (1,567 KB)

来源:arXiv cs.AI · arxiv.org