Simulated patients offer a scalable way to train psychotherapy micro-skills such as empathic responding and exploratory probing, but current systems either follow fixed scripts or rely on LLMs that drift unpredictably over long sessions. We present the Adaptive Virtual Patient (AVP), which adapts its disclosure behavior -- from guarded, through moderate openness, to full disclosure -- in response to trainee skill. The AVP is grounded in a structural equation model fit to nearly 2{,}000 hours of real-world psychotherapy transcripts, which quantifies how therapist empathy and exploration shift a patient's openness over time. An LLM generates the AVP's utterances conditioned on a disclosure level that the dynamics module updates each turn. In an 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, with exploration carrying most of the adaptive signal.

翻译：模拟患者为心理治疗微技能（如共情回应和探索性提问）的可扩展训练提供了途径，但现有系统要么遵循固定脚本，要么依赖在长时间会话中不可预测地偏离目标的大型语言模型。我们提出了自适应虚拟患者（AVP），它能根据受训者的技能调整其信息披露行为——从保守，经适度开放，到完全披露。AVP基于拟合近2000小时真实心理治疗转录数据（近2,000小时）的结构方程模型，该模型量化了治疗师的共情与探索如何随时间改变患者的开放程度。一个大型语言模型根据动力学模块每轮更新的披露水平生成AVP的话语。在20名临床医生及受训者参与、涵盖80次会话（1,033轮）的评估中，AVP的信息披露随治疗师的共情与探索程度上升，而仅基于提示的基线模型则保持平稳；消融实验证实，基于经验驱动的参数化方案优于其他替代方案，其中探索性因素承载了最多的自适应信号。