MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation
cs.CL, cs.AI
Submitted: 2026-03-04
Updated: 2026-08-31
Comments: Accepted to EMNLP 2026 (Main Conference)
Code: https://github.com/Lingxi-mental-health/MIND
License: http://creativecommons.org/licenses/by/4.0/
The gist: Psychiatric consultation requires agents to elicit discriminative evidence, map uncertain narratives to diagnostic criteria, and decide when evidence suffices.
Terminology
Abstract
Psychiatric consultation requires agents to elicit discriminative evidence, map uncertain narratives to diagnostic criteria, and decide when evidence suffices. Existing dialogue and retrieval-augmented systems condition policies on raw histories or appended passages, leaving observed evidence, missing checks, differentials, and support reliability entangled. We introduce MIND, a criteria-grounded evidence-state decision interface. At each turn, MIND constructs a typed state containing observed evidence, unresolved criterion checks, active differentials, criterion-linked supports, and reliability metadata. A training-split Psychiatric Reasoning Bank supplies gated supports, turning retrieval into state construction rather than prompt injection. The same state conditions action selection, process rewards, information-gain scoring, and trajectory rectification. Under EMR-grounded simulator protocols, MIND improves accuracy by 8.8 and 7.3 points over strong inference-only, RAG, and RL baselines, with gains transferring to public MDD-5k dialogues. Matched interventions attribute these gains to the shared state rather than prompt length, retrieval text, or formatting. MIND targets screening-level decision support, not autonomous diagnosis. Code is available at https://github.com/Lingxi-mental-health/MIND.Å
Sources
- HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
- Feedback-Aware Monte Carlo Tree Search for Efficient Information Seeking in Goal-Oriented Conversations
- Baichuan-M2: Scaling Medical Capability with Large Verifier System
- GPT-4o System Card
- LLMs Get Lost In Multi-Turn Conversation
- Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models
- HumanLLM: Towards Personalized Understanding and Simulation of Human Nature
- MedDM:LLM-executable clinical guidance tree for clinical decision-making
- DeepSeek-V3 Technical Report
- ChatCounselor: A Large Language Models for Mental Health Support
- "My nose is running.""Are you also coughing?": Building A Medical Diagnosis Agent with Interpretable Inquiry Logics
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Kimi K2: Open Agentic Intelligence
- Aligning Medical Conversational AI through Online Reinforcement Learning with Information-Theoretic Rewards
- From Medical Records to Diagnostic Dialogues: A Clinical-Grounded Approach and Dataset for Psychiatric Comorbidity
- Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Support
- Qwen3 Technical Report
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering