While virtual reality (VR) excels at simulating physical environments, its effectiveness for training complex interpersonal skills is limited by a lack of psychologically plausible virtual humans. This gap is particularly critical in medical education, where communication is a core clinical competency. This paper introduces a framework that integrates large language models (LLMs) into immersive VR to create medically coherent virtual patients with distinct, consistent personalities, based on a modular architecture that decouples personality from clinical data. We evaluated the system in a mixed-methods, within-subjects study with licensed physicians conducting simulated consultations. Results suggest that the approach is feasible and perceived as a rewarding and effective training enhancement. Our analysis highlights key design principles, including a "realism-verbosity paradox" and the importance of challenges being perceived as clinically authentic to support learning.
@article{arxiv.2509.14132,
title = {When Avatars Have Personality: Effects on Engagement and Communication in Immersive Medical Training},
author = {Julia S. Dollis and Iago A. Brito and Fernanda B. Färber and Pedro S. F. B. Ribeiro and Gustavo H. W. Barbosa and Andressa A. Bastos and Rafael T. Sousa and Arlindo R. Galvão Filho},
journal= {arXiv preprint arXiv:2509.14132},
year = {2026}
}