A Multi-Agent AI Simulator for Single-Session Interpersonal Psychotherapy Training: A Pre–Post Proof-of-Concept Study

Background: The integration of generative Artificial Intelligence (GAI) into mental health care represents a pressing scientific and ethical challenge. A critical global shortage of clinicians leaves the absolute majority of the world's population without access to mental health services, creating an urgent imperative for scalable, evidence-based solutions. While Single-Session Interventions (SSIs) offer a scalable modality, their deployment is constrained by the "human factor"-specifically, the critical shortage of trained professionals and community gatekeepers. However, a critical bottleneck remains while theoretical dissemination is feasible, the mass acquisition of clinical skills is impossible to scale, as high-fidelity training relies entirely on scarce human supervision. In this study, we propose a model for scalable professional training aimed at improving mental health outcomes at scale and resolving implementation barriers through a multi-Agent architecture. Specifically, we constructed and evaluated agents for Single-Session Interpersonal Psychotherapy (IPT-SSI) to demonstrate the "Scale on Scale" paradigm.Method: Employing a mixed-methods design, this study developed and evaluated a novel AI-powered simulator for IPT-SSI. The system utilizes a Multi-Agent architecture (Trainee-Patient-Supervisor) where trainees engaged with a virtual patient to conduct a single-session intervention, receiving real-time and post-session clinical supervision. The system facilitates simultaneous mass practice, allowing unlimited numbers of practitioners to acquire complex skills concurrently within a safe, controlled environment. MHPs (N=72) completed a blended training program comprising a brief didactic unit and an experiential, supervised AI simulation.Results: Quantitative analysis demonstrated robust and statistically significant pre–post gains across key domains: IPT-SSI knowledge self-efficacy, attitudes toward intervention efficacy, and willingness to deliver the intervention. Conversely, changes in reported apprehension regarding delivery did not reach statistical significance. Qualitative evaluation confirmed that the system functioned as a high-fidelity clinical gymnasium, providing a safe space for deliberate practice. The machine’s contribution to human skill formation was perceived as high, successfully balancing rigorous adherence to the evidence-base with supportive, real-time scaffolding.Conclusions: The findings validate the "Scale on Scale" paradigm, demonstrating that a Multi-Agent System can construct a complex, holistic pedagogical environment capable of facilitating simultaneous mass practice. By applying this architecture to IPT-SSI, the study illustrates a method for scaling evidence-based interventions without compromising fidelity. Ultimately, this approach may transform GAI from a theoretical promise into a systemic enabler, enhancing human capabilities to deliver safe, high-fidelity care in resource-constrained settings.