Search papers, labs, and topics across Lattice.
This paper introduces CCD-CBT, a multi-agent framework for simulating Cognitive Behavioral Therapy (CBT) that dynamically reconstructs a Cognitive Conceptualization Diagram (CCD) using a Control Agent and employs information-asymmetric interaction between Therapist and Client Agents. They generate CCDCHAT, a synthetic multi-turn CBT dataset, and fine-tune models on it. Results show that models fine-tuned on CCDCHAT outperform strong baselines in counseling fidelity and positive-affect enhancement, validated by clinical scales and expert therapists, highlighting the importance of dynamic CCD guidance and asymmetric agent design.
Simulating realistic Cognitive Behavioral Therapy requires dynamically updating cognitive models and information-asymmetric agent interactions, a departure from static, omniscient approaches.
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.