# PatientAct: Theory-Grounded Mental Health Client Simulation

arXiv: https://arxiv.org/abs/2608.12750 · HTML: https://mlsanity.com/paper/2608.12750/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles](https://mlsanity.com/paper/2407.00870/) (2024)
- [AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation](https://mlsanity.com/paper/2506.00551/) (2025)
- [Chatbots for Mental Health Support: Exploring the Impact of Emohaa on Reducing Mental Distress in China](https://mlsanity.com/paper/2209.10183/) (2022)
- [Consistent Client Simulation for Motivational Interviewing-based Counseling](https://mlsanity.com/paper/2502.02802/) (2025)
- [PSYCHE: A Multi-faceted Patient Simulation Framework for Evaluation of Psychiatric Assessment Conversational Agents](https://mlsanity.com/paper/2501.01594/) (2025)
- [Can You Share Your Story? Modeling Clients' Metacognition and Openness for LLM Therapist Evaluation](https://mlsanity.com/paper/2507.19643/) (2025)
- [Trust Modeling in Counseling Conversations: A Benchmark Study](https://mlsanity.com/paper/2501.03064/) (2025)
- [PatientHub: A Unified Framework for Patient Simulation](https://mlsanity.com/paper/2602.11684/) (2026)
- [Patient-Zero: Scaling Synthetic Patient Agents to Real-World Distributions without Real Patient Data](https://mlsanity.com/paper/2509.11078/) (2025)
- [Synthetic or Authentic? Building Mental Patient Simulators from Longitudinal Evidence](https://mlsanity.com/paper/2603.22704/) (2026)
- [CandorMD: An AI-Assisted Audio Simulation and Feedback System for Training Clinicians for Medical Error Disclosure](https://mlsanity.com/paper/2605.20701/) (2026)

## Built on by (most cited first, 1 of 1)

- [Disclosure-Gated User Simulation for Companion-Agent Evaluation](https://mlsanity.com/paper/2609.00982/) (2026)

## Abstract (arXiv)

LLM-based simulated clients are increasingly used to train novice counselors, evaluate LLM therapists, and generate synthetic data. However, current simulators produce overly cooperative clients that disclose too readily, accept therapeutic reframes without resistance, and resolve core issues within a single session. We trace these issues to profiles that lack causal depth and behavioral mechanisms that treat all content as equally accessible. We present PatientAct, a framework for client simulation grounded in established clinical theories. Our profiles integrate the 5Ps clinical case formulation, providing causal depth without tying the design to any single therapeutic modality. During simulation, profiles include a dynamic memory layer in which items carry trust thresholds (e.g., symptoms are available early, whereas formative memories require a sustained therapeutic alliance). At each turn, the client's emotional reaction and behavior are modeled before generating a response. If the therapist approaches gated content, PatientAct expresses resistance in terms of quantity, content, and style rather than defaulting to cooperation or a single resistance pattern. We evaluate our framework on 40 clinical situations and demonstrate that it generates diverse profiles with high clinical plausibility. Moreover, PatientAct significantly outperforms the baselines, yielding substantial gains in resistance quality and behavioral realism. Our code and data are publicly available via github.com/Sahandfer/PatientHub.