The Empirically Grounded Adaptive Virtual Patient for Psychotherapy Training

Angela Chen, Siwei Jin, Catherine Bao, Canwen Wang, Robert E. Kraut, Tongshuang Wu, Haiyi Zhu — cs.CY, cs.HC

The Adaptive Virtual Patient (AVP) is an LLM-driven simulated patient for psychotherapy training that adapts its disclosure behavior — from guarded through moderate openness to full disclosure — in response to trainee skill. Grounded in a structural equation model fit to nearly 2,000 hours of real-world psychotherapy transcripts, the AVP quantifies how therapist empathy and exploration shift patient openness. An LLM generates utterances conditioned on a disclosure level updated each turn by the dynamics module. In evaluation with 20 clinicians and trainees over 80 sessions (1,033 turns), the AVP's disclosure rises in response to therapist empathy and exploration, while a prompt-only baseline stays flat; ablations confirm that the empirically motivated parameterization outperforms alternatives. This represents a significant advance in Intelligent Tutoring for professional training domains where authentic practice opportunities are scarce and where existing role-play systems lack grounded, adaptive behavior.

Connected Concepts

Intelligent Tutoring

Connected Articles

Edumirror Educational Social Dynamics — EduMirror: Modeling Educational Social Dynamics with Value-driven Multi-agent Simulation

Bridging Instructional Design Framework Math — WIP: Bridging the Gap Between Instructional Design and Pedagogical Use: A Framework for Mathematics Educators

GenAI Academic Search Workshop — Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS)

Cognitive Offloading LLM Synthesis Writing — Profiling cognitive offloading in LLM-mediated synthesis writing: Volume vs. content

Tibetcpr AI Training Feedback — TibetCPR: A Multimodal Tactile Feedback System for CPR Training in High-Altitude Regions

Student Misconceptions Conditionals Loops Taxonomy — How Students (Mis)understand Conditionals and Loops -- A Taxonomy

Citation

Chen, A., Jin, S., Bao, C., Wang, C., Kraut, R. E., Wu, T., & Zhu, H. (2026). The Empirically Grounded Adaptive Virtual Patient for Psychotherapy Training: Disclosure That Responds to Therapist Micro-Skills. arXiv:2606.10051.