cs.CLNov 16, 2026

SimAI: Mechanistic User Simulation through Psychological Network Models

Authors: Cheng Li, Adhyyan Narang, Jiayi Yuan, John F. Buss, Jina Suh, Devon Sandel-Fernandez, Yulia Tsvetkov, Adam M. Kuczynski, 

Organizations: Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA, USA · Department of Electrical & Computer Engineering, University of Washington, Seattle, WA, USA · Department of Psychiatry and Behavioral Sciences, University of Washington School of Medicine, Seattle, WA, USA

Abstract

Realistic user simulation enables the study of human interactions when direct experimentation is costly or potentially harmful. However, existing simulators largely overlook the psychological mechanisms that drive user behavior. We introduce SimAI, a framework for mechanistic user simulation that models how psychological factors interact to shape user responses. To overcome the challenge of supervising open-ended behavior, we propose a graph reconstruction objective that provides graph-level rewards based on how well simulated conversations reflect the underlying psychological relationships. To support this approach, we construct PSYCHE, a dataset of 18,576 profile-network pairs derived from 516 psychotherapy cases. Automatic evaluations show that SimAI achieves greater simulation and behavioral diversity than existing patient simulators while maintaining strong profile alignment. In an interactive study with 30 mental-health professionals and trainees, SimAI receives the highest average ratings for conversational authenticity, realistic help-seeking behavior, and clinical training utility. Beyond simulation quality, SimAI enables realistic clinical training and uncovers safety failures in prolonged AI interactions with vulnerable users. Code is available at https://github.com/behavioral-data/ANGEL-UserSim.

Figures & tables

Appendix figures & tables27 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. TRACER: Trajectory-Aligned Learning for Multi-Turn User Simulation

    Sep 23, 2026Geng Chen, Ruotong Pan, Zhirui Yang +9AI Agent BenchmarksUser Simulation

  2. Learning User Representations to Improve Simulation Fidelity

    Oct 15, 2026Shuhaib Mehri, Philippe Laban, Michel Galley +3User SimulationUser Modeling