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

2026-04-07

AI Summary

This work addresses the limitations of existing large language model–based simulations of cognitive behavioral therapy (CBT), which typically rely on static cognitive profiles and omniscient single-agent architectures that fail to capture the dynamic progression and information asymmetry inherent in real therapeutic interactions. To overcome these shortcomings, the authors propose CCD-CBT, a novel multi-agent framework that integrates a dynamically reconstructed cognitive conceptualization graph with an information-asymmetric interaction mechanism. In this framework, therapist and client agents collaboratively update the cognitive map, and models are fine-tuned using the synthetic dataset CCDCHAT. Experimental results demonstrate that CCD-CBT significantly outperforms baseline approaches in both counseling fidelity and enhancement of positive affect. Expert evaluations and ablation studies further confirm the model’s clinical interpretability and realism.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Adversarial Agents
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Cognitive Behavioral Therapy
• multi-agent simulation
• information asymmetry
• dynamic cognitive modeling
• conversational agents

Innovation

• Cognitive Conceptualization Diagram
• multi-agent simulation
• information asymmetry
• dynamic reconstruction
• CBT dialogue system