MACBT：一种具有纵向记忆的多智能体认知行为治疗决策支持系统

中文摘要 AI 辅助

认知行为疗法（CBT）是一种基于证据的抑郁症一线治疗方法，然而其推广规模受到临床医生在治疗前准备、治疗后记录以及纵向认知病理追踪方面所花费时间的限制。我们提出了一种面向临床医生的AI决策支持系统，该系统将多智能体CBT框架（MACBT）与CBT专用的纵向记忆模块（CD Memory）相结合。MACBT将CBT的五阶段工作流程（评估、苏格拉底式提问、认知重构、行为实验和治疗监测）编码为五个协作智能体。CD Memory跨会话追踪认知扭曲的类型、频率、严重程度和重构效果，以生成治疗前病理报告和干预优先级建议。我们通过双角色大语言模型模拟构建了一个中文CBT对话语料库，并使用监督微调和直接偏好优化训练了Qwen3-14B骨干模型。使用GPT-4评估者进行的评估显示，MACBT在专业性（2.62）和临床真实性（2.25）方面优于MeChat、SoulChat、PsyChat和CPsyCounX。完整的记忆增强系统进一步将会话质量提高了12.6%，并在跨会话连续性、干预进展和个性化方面实现了2.29的纵向平均得分。

英文摘要

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.

发表机构

• Tsinghua University（清华大学）
• Hangzhou Municipal Health Commission（杭州市卫生健康委员会）
• Hangzhou Women’s Hospital (Hangzhou Maternity and Child Health Care Hospital)（杭州市妇产科医院（杭州市妇幼保健院））
• Hangzhou Fushu Health Technology Co., Ltd（杭州福树健康科技有限公司）

机构由 AI 辅助整理，请以论文原文为准。