WiseMind: a knowledge-guided multi-agent framework for accurate and empathetic psychiatric diagnosis

arXiv cs.CL / 4/6/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces WiseMind, a knowledge-guided multi-agent LLM framework aimed at improving both diagnostic accuracy and empathetic communication in psychiatric assessment.
WiseMind combines a “Reasonable Mind” agent for evidence-based clinical reasoning with an “Emotional Mind” agent for psychologically attuned, supportive dialogue, drawing inspiration from Dialectical Behavior Therapy.
It uses a DSM-5-guided Structured Knowledge Graph to steer diagnostic questioning and reduce hallucinations versus standard prompting approaches.
Evaluations across simulated standard patients and real user sessions (1206 simulated conversations and 180 real sessions) report 85.6% top-1 diagnostic accuracy and stronger differential diagnosis performance than prior state-of-the-art LLM methods.
Psychiatrist expert review indicates WiseMind’s outputs are both clinically sound and psychologically supportive, suggesting feasibility of reliable, empathetic psychiatric AI agents with human oversight.

Abstract

Large Language Models (LLMs) offer promising opportunities to support mental healthcare workflows, yet they often lack the structured clinical reasoning needed for reliable diagnosis and may struggle to provide the emotionally attuned communication essential for patient trust. Here, we introduce WiseMind, a novel multi-agent framework inspired by the theory of Dialectical Behavior Therapy designed to facilitate psychiatric assessment. By integrating a "Reasonable Mind" Agent for evidence-based logic and an "Emotional Mind" Agent for empathetic communication, WiseMind effectively bridges the gap between instrumental accuracy and humanistic care. Our framework utilizes a Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5)-guided Structured Knowledge Graph to steer diagnostic inquiries, significantly reducing hallucinations compared to standard prompting methods. Using a combination of virtual standard patients, simulated interactions, and real human interaction datasets, we evaluate WiseMind across three common psychiatric conditions. WiseMind outperforms state-of-the-art LLM methods in both identifying critical diagnostic nodes and establishing accurate differential diagnoses. Across 1206 simulated conversations and 180 real user sessions, the system achieves 85.6% top-1 diagnostic accuracy, approaching reported diagnostic performance ranges of board-certified psychiatrists and surpassing knowledge-enhanced single-agent baselines by 15-54 percentage points. Expert review by psychiatrists further validates that WiseMind generates responses that are not only clinically sound but also psychologically supportive, demonstrating the feasibility of empathetic, reliable AI agents to conduct psychiatric assessments under appropriate human oversight.