MAGI: Multi-Agent Guided Interview for Psychiatric Assessment
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916707585490944 |
|---|---|
| author | Bi, Guanqun Chen, Zhuang Liu, Zhoufu Wang, Hongkai Xiao, Xiyao Xie, Yuqiang Zhang, Wen Huang, Yongkang Chen, Yuxuan Peng, Libiao Feng, Yi Huang, Minlie |
| author_facet | Bi, Guanqun Chen, Zhuang Liu, Zhoufu Wang, Hongkai Xiao, Xiyao Xie, Yuqiang Zhang, Wen Huang, Yongkang Chen, Yuxuan Peng, Libiao Feng, Yi Huang, Minlie |
| contents | Automating structured clinical interviews could revolutionize mental healthcare accessibility, yet existing large language models (LLMs) approaches fail to align with psychiatric diagnostic protocols. We present MAGI, the first framework that transforms the gold-standard Mini International Neuropsychiatric Interview (MINI) into automatic computational workflows through coordinated multi-agent collaboration. MAGI dynamically navigates clinical logic via four specialized agents: 1) an interview tree guided navigation agent adhering to the MINI's branching structure, 2) an adaptive question agent blending diagnostic probing, explaining, and empathy, 3) a judgment agent validating whether the response from participants meet the node, and 4) a diagnosis Agent generating Psychometric Chain-of- Thought (PsyCoT) traces that explicitly map symptoms to clinical criteria. Experimental results on 1,002 real-world participants covering depression, generalized anxiety, social anxiety and suicide shows that MAGI advances LLM- assisted mental health assessment by combining clinical rigor, conversational adaptability, and explainable reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18260 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MAGI: Multi-Agent Guided Interview for Psychiatric Assessment Bi, Guanqun Chen, Zhuang Liu, Zhoufu Wang, Hongkai Xiao, Xiyao Xie, Yuqiang Zhang, Wen Huang, Yongkang Chen, Yuxuan Peng, Libiao Feng, Yi Huang, Minlie Computation and Language Automating structured clinical interviews could revolutionize mental healthcare accessibility, yet existing large language models (LLMs) approaches fail to align with psychiatric diagnostic protocols. We present MAGI, the first framework that transforms the gold-standard Mini International Neuropsychiatric Interview (MINI) into automatic computational workflows through coordinated multi-agent collaboration. MAGI dynamically navigates clinical logic via four specialized agents: 1) an interview tree guided navigation agent adhering to the MINI's branching structure, 2) an adaptive question agent blending diagnostic probing, explaining, and empathy, 3) a judgment agent validating whether the response from participants meet the node, and 4) a diagnosis Agent generating Psychometric Chain-of- Thought (PsyCoT) traces that explicitly map symptoms to clinical criteria. Experimental results on 1,002 real-world participants covering depression, generalized anxiety, social anxiety and suicide shows that MAGI advances LLM- assisted mental health assessment by combining clinical rigor, conversational adaptability, and explainable reasoning. |
| title | MAGI: Multi-Agent Guided Interview for Psychiatric Assessment |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.18260 |