MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation

TL;DR

This work builds a Criteria-Grounded Psychiatric Reasoning Bank (PRB) that summarizes dialogue context into clinical retrieval states, retrieves semantically similar reference consultations, and distills reusable criteria-grounded clinical supports to guide criteria-aligned inquiry and reasoning.

Abstract

Large language models (LLMs) have advanced medical dialogue systems, yet psychiatric consultation poses substantially higher demands due to subjective ambiguity and comorbidity complexity: an agent must continuously extract psychopathological cues from incomplete and inconsistent patient reports in multi-turn interactions and perform rigorous differential diagnostic reasoning. However, existing methods face two fundamental challenges. First, without criteria-grounded clinical supports, they are prone to unsupported clinical assertions when symptoms are atypical or underspecified. Second, in multi-turn interactions, they struggle to mitigate inquiry drift (off-topic or low-yield questioning) and optimize questioning strategies. To address these challenges, we propose MIND, a unified inquiry--diagnosis reinforcement learning framework for psychiatric consultation. Specifically, we build a Criteria-Grounded Psychiatric Reasoning Bank (PRB) that summarizes dialogue context into clinical retrieval states, retrieves semantically similar reference consultations, and distills reusable criteria-grounded clinical supports to guide criteria-aligned inquiry and reasoning. Building on this foundation, MIND enforces explicit clinical reasoning with rubric-based process rewards to provide fine-grained supervision over intermediate decision steps, and incorporates a value-aware trajectory rectification mechanism to jointly improve information acquisition and diagnostic decision-making across turns. Extensive experiments demonstrate that MIND consistently outperforms strong baselines in diagnostic accuracy, empathetic interaction quality, interpretability, and generalization.

Figures (7)

• Figure 1: Examples illustrate key challenges in psychiatric consultation. (a) shows weak criteria grounding that yields unsupported clinical assertions, while (b) demonstrates inquiry drift in multi-turn dialogues that reduces the acquisition of diagnostically informative cues.
• Figure 2: Motivating examples. (a) shows support-guided inquiry using criteria-grounded supports retrieved from the PRB, and (b) illustrates inquiry drift and value-aware trajectory rectification.
• Figure 3: The overall architecture of MIND. The left module constructs a criteria-grounded Psychiatric Reasoning Bank (PRB) that stores clinical supports, the middle module enforces explicit clinical reasoning, and the right module applies value-aware trajectory rectification to improve the effectiveness and stability of multi-turn psychiatric consultations.
• Figure 4: Radar comparison of diagnostic and dialogue-quality metrics under multi-reward RL.
• Figure 5: Overview of our multi-turn psychiatric consultation framework and training pipeline.