Psychiatric clinical interviewing is a core yet challenging skill for psychiatric residents, requiring clinicians to navigate open-ended dialogue, interpret emotional cues, and manage diagnostic uncertainty. However, existing simulation-based education (SBE) tools often fail to provide sufficient opportunities for realistic and autonomous interview practice, largely due to their reliance on scripted and rigid interactions. In this paper, we explore how large language model (LLM) agents can be leveraged to support SBE systems for psychiatric clinical interview training. We first conducted a formative study to identify the psychiatry-specific learning needs and interactional challenges that should shape system design. Based on these insights, we developed PsyMooc, an LLM-enhanced SBE system designed to support open-ended interview interactions and deliver context-aware, competency-oriented feedback through LLM-driven agents. We then evaluated PsyMooc through a small-scale between-subjects user study to examine usability and learning-related outcomes. The results provide preliminary evidence that PsyMooc was perceived as usable and engaging, and was associated with improvements in residents’ clinical confidence, interview performance proxies, and patient-centered communication behaviors.

Operational skill learning, inherently physical and reliant on hands-on practice and kinesthetic feedback, has yet to be effectively replicated in large language model (LLM)-supported training. Current LLM training assistants primarily generate customized textual feedback, neglecting the crucial kinesthetic modality. This gap derives from the textual and uncertain nature of LLMs, compounded by concerns on user acceptance of LLM driven body control. To bridge this gap and realize the potential of collaborative human-LLM action, this work explores human experience of LLM driven kinesthetic assistance. Specifically, we introduced an "Align-Analyze-Adjust" strategy and developed FlightAxis, a tool that integrates LLM with Electrical Muscle Stimulation (EMS) for flight skill acquisition, a representative operational skill domain. FlightAxis learns flight skills from manuals and guides forearm movements during simulated flight tasks. Our results demonstrate high user acceptance of LLM-mediated body control and significantly reduced task completion times. Crucially, trainees reported that this kinesthetic assistance enhanced their awareness of operation flaws and fostered increased engagement in the training process, rather than relieving perceived load. This work demonstrated the potential of kinesthetic LLM training in operational skill acquisition.