CCD-CBT：基于认知概念图的多智能体治疗交互
CCD-CBT: Multi-Agent Therapeutic Interaction for CBT Guided by Cognitive Conceptualization Diagram
AI总结：
本文提出CCD-CBT框架，通过动态重构认知概念图和信息不对称交互提升CBT模拟效果，基于合成数据集验证了其在治疗可信度和积极情绪增强方面的优势。
摘要：
大型语言模型在模拟认知行为疗法（CBT）顾问方面显示出规模化心理健康支持的潜力。然而，现有方法常依赖静态认知档案和全知单智能体模拟，无法捕捉真实治疗的动态性和信息不对称特性。本文引入CCD-CBT，一种多智能体框架，沿两个轴向改变CBT模拟：1）从静态到动态重构的认知概念图（CCD），由专门的控制智能体更新；2）从全知到信息不对称交互，其中治疗师智能体必须从推断的客户状态进行推理。我们发布了CCDCHAT，一个基于此框架生成的合成多轮CBT数据集。使用临床量表和专家治疗师的评估显示，经过CCDCHAT微调的模型在咨询可信度和积极情绪增强方面优于强基线模型，消融实验确认了动态CCD指导和不对称智能体设计的必要性。本工作为构建理论支撑、临床合理的对话智能体提供了新范式。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
