Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Models

• URL: http://arxiv.org/abs/2607.02983v1
• Date: Fri, 03 Jul 2026 05:43:00 GMT
• Title: Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Models
• Abstract summary: We formalize medical diagnosis as an Iterative Evidence-Seeking Task.<n>We leverage Reinforcement Learning with Verifiable Rewards (RLVR) to elicit intrinsic reasoning within a closed-loop environment.<n>We introduce the Retrieval-Augmented Generation-based Examination Simulator (RAGES), a high-fidelity clinical oracle that provides realistic, knowledge-grounded follow-up evidence.
• Score: 35.9432019263596
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent reasoning-centric Large Language Models (LLMs) have made significant strides, yet they predominantly operate on a passive-inference pattern that assumes complete information. In contrast, real-world clinical intelligence is inherently an iterative investigative process requiring strategic evidence acquisition. To bridge this gap, we formalize medical diagnosis as an Iterative Evidence-Seeking Task. We leverage Reinforcement Learning with Verifiable Rewards (RLVR) to elicit intrinsic reasoning within a closed-loop environment, guided by a novel suite of rewards that enforce diagnostic precision and examination consistency. To facilitate this, we introduce the Retrieval-Augmented Generation-based Examination Simulator (RAGES), a high-fidelity clinical oracle that provides realistic, knowledge-grounded follow-up evidence. Empirical results across diverse datasets demonstrate that our framework enables LLMs to transition from passive responders to autonomous assistants. Notably, our model demonstrates comparable performance to larger and reasoning-enhanced baselines, while RAGES proves superior to vanilla LLMs in generating biologically plausible clinical feedback.

Related papers

• Teaching LLMs How ICU Physicians Approach Clinical Reasoning Through OMOP-Aligned Retrieval Improves Reasoning Across Clinical Domains [4.268872573319899]
  We introduce ICU-REACT, a reasoning dataset developed with 19 clinicians through a clinician-in-the-loop framework.<n>We fine-tuned Clin-REACT models spanning 8B-70B parameters and three model families.<n>Across five clinical reasoning benchmarks, Clin-REACT consistently outperformed its backbone models and open-source general-purpose and medical LLMs.
  arXiv  Detail & Related papers  (2026-08-23T22:14:04Z)
• From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning [17.420995251535647]
  Large Language Models (LLMs) produce "correct answers through flawed reasoning"<n>In this paper, we establish a framework for trustworthy clinical argumentation by adapting the Toulmin model to the diagnostic process.<n>We propose a novel training pipeline: Curriculum Goal-Conditioned Learning (CGCL)<n> Experiments show that our method achieves diagnostic accuracy and reasoning quality comparable to resource-intensive Reinforcement Learning (RL) methods.
  arXiv  Detail & Related papers  (2026-04-13T07:49:39Z)
• Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs [63.535652574541764]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis.<n>Their application in gastrointestinal endoscopy is currently hindered by two critical limitations.<n>We propose a novel Clinical-Cognitive-Aligned (CogAlign) framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-21T07:47:37Z)
• CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework [29.22693846221723]
  We introduce CARE, advancing Clinical Accountability in multi-modal medical Reasoning with an Evidence-grounded agentic framework.<n> CARE decomposes the task into coordinated sub-modules to reduce shortcut learning and hallucination.<n>Our CARE-Flow improves average accuracy by 10.9% over the same size (10B) state-of-the-art (SOTA)
  arXiv  Detail & Related papers  (2026-03-02T08:38:37Z)
• Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis [29.630872344186873]
  Interactive medical consultation requires an agent to proactively elicit missing clinical evidence under uncertainty.<n>Existing evaluations largely remain static or outcome-centric, neglecting the evidence-gathering process.<n>We propose an interactive evaluation framework that explicitly models the consultation process using a simulated patient and a revsimulated reporter grounded in atomic evidences.
  arXiv  Detail & Related papers  (2026-01-27T16:36:35Z)
• Timely Clinical Diagnosis through Active Test Selection [49.091903570068155]
  We propose ACTMED (Adaptive Clinical Test selection via Model-based Experimental Design) to better emulate real-world diagnostic reasoning.<n>LLMs act as flexible simulators, generating plausible patient state distributions and supporting belief updates without requiring structured, task-specific training data.<n>We evaluate ACTMED on real-world datasets and show it can optimize test selection to improve diagnostic accuracy, interpretability, and resource use.
  arXiv  Detail & Related papers  (2025-10-21T18:10:45Z)
• Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models [15.530083855947987]
  We propose the first Multimodal Medical Reasoning-with-Retrieval framework, Med-RwR.<n>Med-RwR actively retrieves external knowledge by querying observed symptoms or domain-specific medical concepts during reasoning.<n> Evaluation on various public medical benchmarks demonstrates Med-RwR's significant improvements over baseline models.
  arXiv  Detail & Related papers  (2025-10-21T05:18:18Z)
• Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models [51.91760712805404]
  We introduce VivaBench, a benchmark for evaluating sequential clinical reasoning in large language models (LLMs)<n>Our dataset consists of 1762 physician-curated clinical vignettes structured as interactive scenarios that simulate a (oral) examination in medical training.<n>Our analysis identified several failure modes that mirror common cognitive errors in clinical practice.
  arXiv  Detail & Related papers  (2025-10-11T16:24:35Z)
• End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning [52.12425911708585]
  Deep-DxSearch is an agentic RAG system trained end-to-end with reinforcement learning (RL)<n>In Deep-DxSearch, we first construct a large-scale medical retrieval corpus comprising patient records and reliable medical knowledge sources.<n> Experiments demonstrate that our end-to-end RL training framework consistently outperforms prompt-engineering and training-free RAG approaches.
  arXiv  Detail & Related papers  (2025-08-21T17:42:47Z)
• Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications [59.721265428780946]
  Large Language Models (LLMs) in medicine have enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning.<n>This paper provides the first systematic review of this emerging field.<n>We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies and test-time mechanisms.
  arXiv  Detail & Related papers  (2025-08-01T14:41:31Z)
• Beyond Self-Consistency: Ensemble Reasoning Boosts Consistency and Accuracy of LLMs in Cancer Staging [0.33554367023486936]
  Cancer staging status is available in clinical reports, but it requires natural language processing to extract it. With the advance in clinical-oriented large language models, it is promising to extract such status without extensive efforts in training the algorithms. In this study, we propose an ensemble reasoning approach with the aim of improving the consistency of the model generations.
  arXiv  Detail & Related papers  (2024-04-19T19:34:35Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.