CCD-CBT: Multi-Agent Therapeutic Interaction for CBT Guided by Cognitive Conceptualization Diagram

TL;DR

This paper introduces CCD-CBT, a multi-agent framework for simulated CBT that dynamically updates a cognitive diagram and models asymmetric therapist-client interactions, improving clinical plausibility.

Contribution

It proposes a novel multi-agent approach with dynamic cognitive modeling and asymmetric interaction, advancing scalable, theory-grounded mental health support.

Findings

Models fine-tuned on CCDCHAT outperform baselines in counseling fidelity.

Dynamic CCD guidance and asymmetric agent design are crucial for performance.

Evaluations show improved positive-affect enhancement and clinical plausibility.

Abstract

Large language models show potential for scalable mental-health support by simulating Cognitive Behavioral Therapy (CBT) counselors. However, existing methods often rely on static cognitive profiles and omniscient single-agent simulation, failing to capture the dynamic, information-asymmetric nature of real therapy. We introduce CCD-CBT, a multi-agent framework that shifts CBT simulation along two axes: 1) from a static to a dynamically reconstructed Cognitive Conceptualization Diagram (CCD), updated by a dedicated Control Agent, and 2) from omniscient to information-asymmetric interaction, where the Therapist Agent must reason from inferred client states. We release CCDCHAT, a synthetic multi-turn CBT dataset generated under this framework. Evaluations with clinical scales and expert therapists show that models fine-tuned on CCDCHAT outperform strong baselines in both counseling fidelity and positive-affect enhancement, with ablations confirming the necessity of dynamic CCD guidance and asymmetric agent design. Our work offers a new paradigm for building theory-grounded, clinically-plausible conversational agents.