arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2606.17789cs.HC

Mind Companion: 一种用于基于过程心理治疗的具身对话代理

Mind Companion: An Embodied Conversational Agent for Process-Based Psychotherapy

Sofie Kamber, Lukas Diebold, Pascal Riachi, Stella Brogna, Andrew Gloster, Rafael Wampfler

AI总结:

提出Mind Companion,一种基于大语言模型的具身对话代理,通过多层级心理分析与过程治疗原则,实时分析客户陈述并生成回应,评估显示GPT-5.2在多个维度上优于人类治疗师。

摘要:

全球范围内获得循证心理治疗的机会仍然有限,即使在高收入地区也存在漫长的等待名单。最近大语言模型(LLM)的进展,在临床监督和安全机制设计下,为可扩展的心理健康支持提供了潜力。我们提出了Mind Companion,一种基于LLM的具身对话代理,将多层级心理分析与基于过程的治疗原则相结合。该系统对客户陈述进行实时分析,涵盖事实提取、心理灵活性过程检测、情绪识别和安全监控。分析结果存储供监督临床医生用于治疗规划。回应生成结合了来自循证治疗文献的检索增强生成和上下文感知提示。回应通过具身化虚拟角色以同步语音合成和动画传递。我们评估了三种LLM配置(GPT-4.1-mini、GPT-5.2、Claude Sonnet 4.5),与来自真实治疗会话的治疗师回应进行对比,使用自动LLM裁判评估和11位专业心理治疗师的专家评估。GPT-5.2在理解力、人际效能、协作和治疗一致性方面均获得高于人类治疗师回应的评分,证明了基于LLM的对话代理作为临床护理补充工具的可行性。

英文摘要:

Access to evidence-based psychotherapy remains limited worldwide, with long waitlists even in high-income regions. Recent advances in large language models (LLMs) offer potential for scalable mental health support when designed with clinical oversight and safety mechanisms. We present Mind Companion, an LLM-based embodied conversational agent integrating multi-layered psychological analysis with process-based therapy principles. The system performs real-time analysis of client statements across fact extraction, psychological flexibility process detection, emotion recognition, and safety monitoring. Analysis results are stored for supervising clinicians to inform therapeutic planning. Response generation incorporates retrieval-augmented generation from evidence-based therapeutic literature and context-aware prompting. Responses are delivered through an embodied avatar with synchronized speech synthesis and animation. We evaluated three LLM configurations (GPT-4.1-mini, GPT-5.2, Claude Sonnet 4.5) against therapist responses from real therapy sessions using automated LLM-judge assessment and expert evaluation with 11 professional psychotherapists. GPT-5.2 achieved higher ratings than human therapist responses across understanding, interpersonal effectiveness, collaboration, and therapeutic alignment in both evaluations, demonstrating the feasibility of LLM-based conversational agents as tools to complement clinical care.

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。

↑