arXiv 2607.078242026-07-10cs.MAcs.AI

从触发因素到情感：基于CPM的评估多智能体模型用于基于角色的对话中的动态情感演变

From Triggers to Emotions: A CPM-Grounded Appraisal Multi-Agent for Dynamic Emotional Evolution in Persona-Based Dialogue

National Centre for Computer Animation（国家计算机动画中心）；Information Hub（信息中心）；Key Laboratory of Child Cognition & Behavior Development of Hainan Province（海南省儿童认知与行为发展重点实验室）；Chief Technology Officer（首席技术官）；School of Health and Care（健康与护理学院）

Jingyao Cai, Shuaijun Liu, Abdul Rehman, Yutong Guo, Qin Tian, Thomas Dolby, Sue Green, Chantel Cox, Xiaosong Yang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对基于角色对话中情感模拟的局限，借鉴CPM理论提出CPM - MultiAgent框架，通过情感触发提取、协作评估和状态更新实现情感一致的角色模拟，经多种实验验证能有效模拟动态情感演变。

摘要：

大语言模型推动了基于角色的对话智能体在情感敏感角色模拟方面的发展，但相关工作存在关键差距。基于角色的对话系统常将情感编码为静态特征或表面风格线索，情感对话研究多关注对用户的共情反应生成而非建模智能体角色自身演变的情感状态。为解决这一局限，我们从将情感视为由外部事件评估塑造的动态过程的组件过程模型（CPM）中汲取灵感，提出CPM - MultiAgent框架。该框架将角色情感表示为潜在状态，通过情感触发因素提取、基于CPM的协作评估和情感状态更新，在多轮对话中实现更情感一致的角色模拟。与基线比较、消融研究、人工评估和案例分析表明，CPM - MultiAgent能有效模拟情感敏感角色模拟设置中的动态情感演变。

英文摘要：

Large Language Models (LLMs) have substantially advanced persona-based dialogue agents for emotion-sensitive role simulation in healthcare, education, counseling, customer service, and interactive storytelling. However, two related lines of work leave a key gap. Persona-based dialogue systems often encode emotions as static traits or surface-level stylistic cues, and affective dialogue research has largely focused on empathetic response generation toward users rather than modeling the agent persona's own evolving emotional state. As a result, trigger-driven emotional evolution within a character remains underexplored. To address this limitation, we draw inspiration from the Component Process Model (CPM), a psychological theory that views emotion as a dynamic process shaped by the appraisal of external events. We propose CPM-MultiAgent, a CPM-grounded emotion evolution multi-agent framework for supporting emotional changes in persona-based dialogue. Instead of treating a character's emotion as a fixed attribute, CPM-MultiAgent represents it as a latent state that is continuously reshaped by dialogue triggers. Through affective trigger extraction, CPM-based collaborative appraisal, and emotion state updating, the framework enables more emotionally consistent role simulation in multi-turn interactions.Experiments with baseline comparisons, ablation studies, human evaluation, and case analyses demonstrate that CPM-MultiAgent effectively models dynamic emotional evolution in emotionally sensitive role-simulation settings.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。