# Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosis

arXiv: https://arxiv.org/abs/2508.11398 · HTML: https://mlsanity.com/paper/2508.11398/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 38 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 14 of 14)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions](https://mlsanity.com/paper/2310.14724/) (2023)
- [Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions](https://mlsanity.com/paper/2503.22678/) (2025)
- [Challenges of Large Language Models for Mental Health Counseling](https://mlsanity.com/paper/2311.13857/) (2023)
- [MDD-5k: A New Diagnostic Conversation Dataset for Mental Disorders Synthesized via Neuro-Symbolic LLM Agents](https://mlsanity.com/paper/2408.12142/) (2024)
- [A Systematic Evaluation of LLM Strategies for Mental Health Text Analysis: Fine-tuning vs. Prompt Engineering vs. RAG](https://mlsanity.com/paper/2503.24307/) (2025)
- [LLM Questionnaire Completion for Automatic Psychiatric Assessment](https://mlsanity.com/paper/2406.06636/) (2024)
- [A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions](https://mlsanity.com/paper/2502.11095/) (2025)
- [Rethinking the Alignment of Psychotherapy Dialogue Generation with Motivational Interviewing Strategies](https://mlsanity.com/paper/2408.06527/) (2024)
- [CausalMed: Causality-Based Personalized Medication Recommendation Centered on Patient health state](https://mlsanity.com/paper/2404.12228/) (2024)
- [Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therapeutic Strategies for Psychotherapy](https://mlsanity.com/paper/2411.06723/) (2024)
- [Large Language Models for Interpretable Mental Health Diagnosis](https://mlsanity.com/paper/2501.07653/) (2025)
- [Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment](https://mlsanity.com/paper/2507.05528/) (2025)
- [Natural Language-Assisted Multi-modal Medication Recommendation](https://mlsanity.com/paper/2501.07166/) (2025)

## Built on by (most cited first, 8 of 8)

- [XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being](https://mlsanity.com/paper/2603.06583/) (2026)
- [MAGneT: Coordinated Multi-Agent Generation of Synthetic Multi-Turn Mental Health Counseling Sessions](https://mlsanity.com/paper/2509.04183/) (2025)
- [Toward Zero-Egress Psychiatric AI: On-Device LLM Deployment for Privacy-Preserving Mental Health Decision Support](https://mlsanity.com/paper/2604.18302/) (2026)
- [DELTA: Deliberative Multi-Agent Reasoning with Reinforcement Learning for Multimodal Psychological Counseling](https://mlsanity.com/paper/2602.04112/) (2026)
- [Trust Stack for Mental Health AI: A Survey of Calibration across Human, Interaction, and AI Layers](https://mlsanity.com/paper/2604.20166/) (2026)
- [StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation](https://mlsanity.com/paper/2605.27393/) (2026)
- [SSR: Can Simulated Patients Learn to Stigmatize Themselves? Modeling Self-Stigma through Internal Monologue](https://mlsanity.com/paper/2606.08254/) (2026)
- [Expert-Level Crisis Detection in Mental Health Conversations](https://mlsanity.com/paper/2606.10380/) (2026)

## Abstract (arXiv)

LLM-based agents have emerged as transformative tools capable of executing complex tasks through iterative planning and action, achieving significant advancements in understanding and addressing user needs. Yet, their effectiveness remains limited in specialized domains such as mental health diagnosis, where they underperform compared to general applications. Current approaches to integrating diagnostic capabilities into LLMs rely on scarce, highly sensitive mental health datasets, which are challenging to acquire. These methods also fail to emulate clinicians' proactive inquiry skills, lack multi-turn conversational comprehension, and struggle to align outputs with expert clinical reasoning. To address these gaps, we propose DSM5AgentFlow, the first LLM-based agent workflow designed to autonomously generate DSM-5 Level-1 diagnostic questionnaires. By simulating therapist-client dialogues with specific client profiles, the framework delivers transparent, step-by-step disorder predictions, producing explainable and trustworthy results. This workflow serves as a complementary tool for mental health diagnosis, ensuring adherence to ethical and legal standards. Through comprehensive experiments, we evaluate leading LLMs across three critical dimensions: conversational realism, diagnostic accuracy, and explainability. Our datasets and implementations are fully open-sourced.