Training psychotherapists in evidence-based interventions such as Acceptance and Commitment Therapy (ACT) requires repeated practice with meaningful feedback, yet opportunities for safe, standardized training are limited by ethical, logistical, and resource constraints. We introduce a system designed to support ACT-oriented psychotherapy training through spoken dialogue with an embodied virtual patient. The system uses large language models to simulate patient behavior conditioned on profiles derived from real therapy sessions and configurable clinical scenarios, while a separate automated evaluator provides turn-by-turn feedback on therapist responses based on established ACT fidelity criteria. Rather than aiming to replace supervision, the system is intended to support deliberate practice by enabling experimentation, reflection, and immediate feedback in low-risk settings. Expert evaluation with practicing psychologists confirmed high realism in patient behavior and demonstrated that immediate turn-by-turn ACT feedback increased therapists' awareness of intervention choices and enabled effective experimentation with alternative responses. Quantitative evaluation across 49 therapy transcripts identified GPT-4o-mini as the optimal feedback model, achieving the lowest mean absolute error (MAE = 6.12) in replicating human supervisor ACT fidelity ratings with statistically significant agreement. This work demonstrates the potential of fidelity-aware simulated patients as a scalable complement to psychotherapy training.

翻译：培训心理治疗师掌握循证干预方法（如接纳与承诺疗法，ACT）需要反复实践并给予有意义的反馈，然而伦理、后勤和资源限制制约了安全、标准化训练的机会。我们引入一个旨在通过具身虚拟患者的语音对话支持ACT导向心理治疗培训的系统。该系统利用大语言模型模拟患者行为，其行为条件基于真实治疗会话衍生出的配置文件及可配置的临床场景；同时，独立自动评估器依据既定的ACT保真度标准，为治疗师回应提供逐轮反馈。系统目标并非替代督导，而是通过低风险环境中的实验、反思和即时反馈，支持刻意练习。执业心理学家的专家评估证实了患者行为的高度真实性，并表明即时逐轮ACT反馈提升了治疗师对干预选择的觉察，使其能够有效尝试替代回应。基于49份治疗记录的定量评估显示，GPT-4o-mini在复现人类督导的ACT保真度评分中取得最低平均绝对误差（MAE = 6.12），且具有统计显著性一致性。本研究展示了具有保真度意识的模拟患者作为心理治疗培训可扩展补充工具的潜力。