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

Jun 1, 2026·
S. Kamber
,
L. Diebold
,
P. Riachi
,
S. Brogna
,
A. Gloster
Dr. Rafael Wampfler
Rafael Wampfler
Abstract
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.
Type
Publication
In Proceedings of the 2026 IEEE International Conference on Healthcare Informatics (ICHI ‘26), Minneapolis, USA, pp. 984–993
publications
Mental Health AI Psychotherapy Embodied Conversational Agents Large Language Models Acceptance and Commitment Therapy Safety
Dr. Rafael Wampfler
Authors
Dr. Rafael Wampfler
Senior Researcher & Lecturer

I am a Senior Researcher & Lecturer at the Computer Graphics Laboratory of ETH Zurich, and a Research Consultant at Disney Research. I lead the Digital Character AI team at CGL and, as PI of an SNF Ambizione grant, a line of generative models that produce expressive 3D facial animation from speech and text under explicit control of emotion and expression. My research interests include conversational digital characters, generative animation, affective computing, human-computer interaction, and applied machine learning.

My vision is to create intelligent digital humans that can naturally communicate, understand, and support people across domains such as education and mental health. My research focuses on multimodal artificial intelligence for interactive digital humans, developing models that combine large language models, affective computing, and data-driven animation to create embodied conversational agents endowed with autonomous agency, consistent values, and beliefs.

My work bridges machine learning, human–computer interaction, and computer graphics to enable AI systems such as Digital Einstein and interactive patient avatars for psychotherapy training and health education.