用动态认知图谱和信息不对称模拟真实认知行为治疗。
CCD-CBT: Multi-Agent Therapeutic Interaction for CBT Guided by Cognitive Conceptualization Diagram
- 构建动态认知概念化图谱，由控制代理实时更新。
- 模型在咨询契合度与积极情绪提升上超越基线。
- 适合心理治疗对话系统研究者与开发者。
大型语言模型有望通过模拟认知行为疗法（CBT）顾问实现可扩展的心理健康支持。然而，现有方法多依赖静态认知画像和全知单代理模拟，难以捕捉真实治疗中动态、信息不对称的特性。本文提出CCD-CBT，一种多智能体框架，沿两个维度革新CBT模拟：1）从静态转向由控制代理动态重构的认知概念化图谱（CCD），2）从全知转向信息不对称交互，治疗代理需基于推断的来访者状态进行推理。我们发布了基于该框架生成的合成多轮CBT数据集CCDCHAT。临床量表与专家治疗师评估显示，基于CCDCHAT微调的模型在咨询契合度和积极情绪增强方面优于强基线，消融实验确认了动态CCD引导与非对称代理设计的必要性。本工作为构建理论基础扎实、临床可信的对话代理提供了新范式。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。