From Triggers to Emotions: A CPM-Grounded Appraisal Multi-Agent for Dynamic Emotional Evolution in Persona-Based Dialogue
For researchers in affective dialogue and persona-based systems, this work provides a psychologically grounded method for dynamic emotion modeling, though it is an incremental step combining existing theories with multi-agent architectures.
The paper addresses the gap in modeling dynamic emotional evolution for persona-based dialogue agents, proposing a CPM-grounded multi-agent framework that treats emotion as a latent state reshaped by dialogue triggers. Experiments show the framework effectively models emotional changes in role-simulation settings.
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.