Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosis
Open accessThe DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“By contrast, systems such as DSM5AgentFlow, although providing structured, evidence-grounded rationales linking patient responses to DSM-5 criteria, primarily generate reasoning narratives that are not formally validated against the underlying decision process and should therefore be interpreted as process-level interpretability [24].”
From Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review (2026) · cites this paper as [24]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These multi-agent systems [66,77,88,102,118] distribute clinical reasoning across specialized agents such as history-takers, evidence retrievers, diagnosticians, and decision-makers, with inter-agent communication channels serving as inherently traceable explanation mechanisms.”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [77]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Ozgun et al. [77] found that high-performing base models sometimes yield the most opaque diagnostic outputs, a counterintuitive result suggesting that raw capability does not automatically translate to transparency.”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [77]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The primary clinical and biomedical tasks addressed included clinical decision support systems (CDSSs) [20,21,22,24,27], question answering (QA) [27], mental health screening and assessment [24], diagnostic and report generation or summarization [20,22,23], drug–target interaction prediction [19], biomarker discovery [25], and single-cell annotation [26].”
From Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review (2026) · cites this paper as [24]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Nine studies met the inclusion criteria.”
From Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review (2026) · cites this paper as [24]
7 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERTScore: Evaluating Text Generation with BERT
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09675 · Cited by 2,865
Stade, E. C., Stirman, S. W., Ungar, L. H., Boland, C. L., Schwartz, H. A., Yaden, D. B., Sedoc, J., DeRubeis, R. J., Willer, R., & Eichstaedt, J. C. (2024) · npj Mental Health Research · doi:10.1038/s44184-024-00056-z · Cited by 391 · cited 3×
“Generating synthetic mental health dialogues is a key strategy to overcome data scarcity while aiming for transparency [14, 28].”
Large Language Models for Mental Health Applications: Systematic Review
Guo, Z., Lai, A., Thygesen, J. H., Farrington, J., Keen, T., & Li, K. (2024) · JMIR Mental Health · doi:10.2196/57400 · Cited by 269 · cited 3×
“Generating synthetic mental health dialogues is a key strategy to overcome data scarcity while aiming for transparency [14, 28].”
A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
Wu, J., Yang, S., Zhan, R., Yuan, Y., Wong, D. F., & Chao, L. S. (2023) · arXiv · doi:10.48550/arxiv.2310.14724 · Cited by 212 · cited 1×
“Largelanguagemodel(LLM)-basedagentshaverapidlyadvanced the automation of complex tasks, demonstrating strong capabilities in planning, reasoning, and adapting to user needs across diverse domains [25, 35].”
A scoping review of large language models for generative tasks in mental health care
Hua, Y., Na, H., Li, Z., Liu, F., Fang, X., Clifton, D., & Torous, J. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01611-4 · Cited by 151
A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions
Na, H., Hua, Y., Wang, Z., Shen, T., Yu, B., Wang, L., Wang, W., Torous, J. B., & Chen, L. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.385 · Cited by 104
Large Language Models in Mental Health Care: A Scoping Review
Hua, Y., Liu, F., Yang, K., Li, Z., Na, H., Sheu, Y.-H., Zhou, P., Moran, L. V., Ananiadou, S., Clifton, D. A., et al. (2025) · Current Treatment Options in Psychiatry · doi:10.1007/s40501-025-00363-y · Cited by 92
Assessing and alleviating state anxiety in large language models
Ben‐Zion, Z., Witte, K., Jagadish, A. K., Duek, O. A., Harpaz‐Rotem, I., Khorsandian, M.-C., Burrer, A., Seifritz, E., Homan, P., Schulz, E., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01512-6 · Cited by 82
Challenges of Large Language Models for Mental Health CounselingPreprint
Chung, N. C., Dyer, G., & Brocki, L. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.13857 · Cited by 82
Ke, Y., Yang, R., Lie, S. A., Lim, T. X. Y., Ning, Y., Li, I., Abdullah, H. R., Ting, D. S. W., & Liu, N. (2024) · Journal of Medical Internet Research · doi:10.2196/59439 · Cited by 64
Research works printed but not linked: 9
- American Psychiatric Association: DSM-5 Level 1 Cross-Cutting Symptom Measure. https://www.psychiatry.org/psychiatrists/practice/dsm/educational-resources/assessment-measures (2024), accessed: 2024-06-09
- BN, S., Mattioli, D., Abdullah, S., Arriaga, R.I., Wiese, C.W., Sherrill, A.M.: How real are synthetic therapy conversations? evaluating fidelity in prolonged exposure dialogues (2025), https://arxiv.org/abs/2504.21800 · arXiv
- De Duro, E., Improta, R., Stella, M.: Introducing CounseLLMe: A dataset of simulated mental health dialogues for comparing LLMs like haiku, LLaMAntino and ChatGPT against humans. Emerging Trends in Drugs, Addictions, and Health textbf5, 100170 (2025)
- Hua, Y., Beam, A., Chibnik, L.B., Torous, J.: From statistics to deep learning: Using large language models in psychiatric research. Psychiatry Research (2025), covers broader LLM use in psychiatric research.
- Sun, X., Pei, J., de Wit, J., Aliannejadi, M., Krahmer, E., Dobber, J.T., Bosch, J.A.: Eliciting motivational interviewing skill codes in psychotherapy with llms: A bilingual dataset and analytical study. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). pp. 5609-5621 (2024)
- Sun, X., Tang, X., El Ali, A., Li, Z., Ren, P., de Wit, J., Pei, J., Bosch, J.A.: Rethinking the alignment of psychotherapy dialogue generation with motivational interviewing strategies. In: Proceedings of the 31st International Conference on Computational Linguistics. pp. 1983-2002 (2025)
- Suresh, S.K., Mengjun, W., Pranav, T., Chng, E.S.: Diasynth: Synthetic dialogue generation framework for low resource dialogue applications (2025), https://arxiv.org/abs/2409.19020 · arXiv
- Thompson, H., Valdimarsdottir, H., Winkel, G., Jandorf, L., Redd, W.: Medical mistrust: A concept analysis. Journal of Advanced Nursing textbf57(6), 558-565 (2007)
- Xu, X., Yao, B., Dong, Y., et al.: Mental-LLM: Leveraging large language models for mental health prediction via online text data. In: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT). vol. 8, p. 32. ACM (2024)
Cited by
Song, H., Kang, M., Shin, J., Kim, J., Park, C., Yoo, H., An, J., Oh, A., Han, J. J., & Lim, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.12871 · Cited by 10
Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review
Collaco, B. G., Prabha, S., Gomez-Cabello, C. A., Haider, S. A., Genovese, A., Wood, N. G., Gopala, N., Raman, R., Hester, E. O., & Forte, A. J. (2026) · Bioengineering · doi:10.3390/bioengineering13050513 · Cited by 3
“The primary clinical and biomedical tasks addressed included clinical decision support systems (CDSSs) [20–22,24, 27 ],”
InfluentialAn Honesty-Aware Multi-Agent Framework for Synthetic Psychiatric Intake Data Generation
Zhang, X., Dao, C., Wang, Z., Pang, Y., & Zhou, J. (2026) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/2026.findings-emnlp.2334 · Cited by 1
StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation
Meng, Q., Chen, M., Liu, D., Mo, Y., Su, Y., Sun, X., Hindriks, K. V., & Pei, J. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.468 · Cited by 1
Self-citationYang, J., Chen, J., Wang, F., Nie, Y., Liu, Y., Duan, Z., & Chen, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.04112 · Cited by 1
Metadata
- Authors
- Ozgun, M. C., Pei, J., Hindriks, K., Donatelli, L., Liu, Q., & Wang, J.
- Affiliations
- Vrije Universiteit Amsterdam (NL)
- Wageningen University & Research (NL)
- Guangzhou University (CN)
- Venue
- Proceedings of the 34th ACM International Conference on Information and Knowledge Management
- Publisher
- ACM
- Published
- 2025-11-10
- Pages
- 2263-2272
- ISSN
- 2155-0751 (ISSN-L)
- OpenAlex
- W4416017478
- Cited by
- 7
- References
- 15
- Citations by year
- 2026: 7
- FWCI
- 7.32
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- ACM International Conference on Information and Knowledge Management (CIKM) (publishedVersion, cc-by)
- VU Research Portal (publishedVersion, cc-by)
- Socio-Environmental Systems Modeling (submittedVersion, cc-by)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- LLM agents, psychiatric diagnosis, multi-agent workflows, explainable AI, trustworthy AI, psychotherapy, clinical reasoning, diagnostic accuracy, mental disorder prediction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosis. https://app.cochat.ai/papers/10.1145/3746252.3761164
- The paper
- Ozgun, M. C., Pei, J., Hindriks, K., Donatelli, L., Liu, Q., & Wang, J. (2025). Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosis. Proceedings of the 34th ACM International Conference on Information and Knowledge Management. https://doi.org/10.1145/3746252.3761164
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.