Ai system helps therapists track depression and plan cbt sessions
MACBT: A Multi-Agent Cognitive Behavioral Therapy Decision Support System with Longitudinal Memory
Artificial Intelligence
Summary
Cognitive behavioral therapy (CBT) is a common way to help people with depression, but therapists spend a lot of time preparing and reviewing notes. The authors created an AI system with multiple agents that work together to follow the steps of CBT and keep track of a patient’s progress across sessions. This system can prepare reports and suggest what to focus on next in therapy sessions. Tests show it performs better than existing therapy chatbots in professionalism and continuity over time.
What this means in practice
- •For mental health clinicians: Support clinicians by automating session preparation, documentation, and personalized intervention planning in CBT treatment for depression.
- •For mental health chatbot developers: Provide a multi-agent framework and longitudinal memory design to improve dialogue quality and clinical authenticity in therapy bots.
Authors
De Jiang, Shuo Zhang, Weiwei Liao, Jianying Zhang, Chuanhui Yu, Hongen Liao, Kehong Yuan
Abstract
Cognitive behavioral therapy (CBT) is an evidence-based first-line treatment for depression, yet its scale is constrained by the time clinicians spend on pre-session preparation, post-session documentation, and longitudinal cognitive-pathology tracking. We present a clinician-facing AI decision-support system that combines a multi-agent CBT framework (MACBT) with a CBT-specific longitudinal memory module (CD Memory). MACBT encodes the five-stage CBT workflow (assessment, Socratic questioning, cognitive restructuring, behavioral experiments, and treatment monitoring) into five collaborative agents. CD Memory tracks cognitive-distortion type, frequency, severity, and restructuring efficacy across sessions to generate pre-session pathology reports and intervention-priority recommendations. We construct a Chinese CBT dialogue corpus via dual-role large language model simulation and train a Qwen3-14B backbone with supervised fine-tuning and direct preference optimization. Evaluation with GPT-4 judges shows MACBT outperforms MeChat, SoulChat, PsyChat, and CPsyCounX in professionalism (2.62) and clinical authenticity (2.25). The full memory-augmented system further improves session quality by 12.6% and achieves a longitudinal mean of 2.29 on cross-session continuity, intervention progression, and personalization.