mlsanityData to 14 Oct 2026

Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning

arXiv 2505.24105 ↗First posted 30 May 2025cs.CLcited by 14

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

We present EHRMIND, a practical recipe for adapting large language models (LLMs) to complex clinical reasoning tasks using reinforcement learning with verifiable rewards (RLVR). While RLVR has succeeded in mathematics and coding, its application to healthcare contexts presents unique challenges due to the specialized knowledge and reasoning required for electronic health record (EHR) interpretation. Our pilot study on the MEDCALC benchmark reveals two key failure modes: (1) misapplied knowledge, where models possess relevant medical knowledge but apply it incorrectly, and (2) missing knowledge, where models lack essential domain knowledge. To address these cases, EHRMIND applies a two-stage solution: a lightweight supervised fine-tuning (SFT) warm-up that injects missing domain knowledge, stabilizes subsequent training, and encourages structured, interpretable outputs; followed by RLVR, which reinforces outcome correctness and refines the model's decision-making. We demonstrate the effectiveness of our method across diverse clinical applications, including medical calculations (MEDCALC), patient-trial matching (TREC CLINICAL TRIALS), and disease diagnosis (EHRSHOT). EHRMIND delivers consistent gains in accuracy, interpretability, and cross-task generalization. These findings offer practical guidance for applying RLVR to enhance LLM capabilities in healthcare settings.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 36 of its 64 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

36 of 64 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Enhancing LLMs' Clinical Reasoning with Real-World Data from a Nationwide Sepsis Registry5 May
  2. 2025ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model13 Apr
  3. 2025PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language Tasks12 Apr
  4. 2025GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning2 Apr
  5. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models18 Mar
  6. 2025Med-RLVR: Emerging Medical Reasoning from a 3B base model via reinforcement Learning27 Feb
  7. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning26 Feb
  8. 2024Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval6 Oct

Other references · 28

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  7. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  8. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  9. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  10. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  11. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learningcited by 336
  12. 2025MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learningcited by 303
16 more
  1. 2025Reinforcement Learning for Reasoning in Large Language Models with One Training Examplecited by 295
  2. 2025Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learningcited by 262
  3. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RLcited by 248
  4. 2024ReFT: Reasoning with Reinforced Fine-Tuningcited by 239
  5. 2025Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domainscited by 156
  6. 2025RM-R1: Reward Modeling as Reasoningcited by 154
  7. 2025DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learningcited by 66
  8. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learningcited by 60
  9. 2025Exploring the Limit of Outcome Reward for Learning Mathematical Reasoningcited by 52
  10. 2025Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuningcited by 44
  11. 2025TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Recordscited by 34
  12. 2025Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learningcited by 33
  13. 2023The Shaky Foundations of Clinical Foundation Models: A Survey of Large Language Models and Foundation Models for EMRscited by 29
  14. 2025Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewardscited by 14
  15. 2025Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domaincited by 7
  16. 2025GenCLS++: Pushing the Boundaries of Generative Classification in LLMs Through Comprehensive SFT and RL Studies Across Diverse Datasetscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 8.

14 papers.

Sort:

By area:

  1. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  2. 2025SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMscited by 24
  3. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 22
  4. 2025EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysiscited by 18
  5. 2026EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generationcited by 6
  6. 2026Reaching Beyond the Mode: RL for Distributional Reasoning in Language Modelscited by 6
  7. 2026Do explanations generalize across large reasoning models?cited by 5
  8. 2025Scalable Stewardship of an LLM-Assisted Clinical Benchmark with Physician Oversightcited by 2
  9. 2026LLMs can construct powerful representations and streamline sample-efficient supervised learningcited by 2
  10. 2026Empowering Locally Deployable Medical Agent via State Enhanced Logical Skills for FHIR-based Clinical Taskscited by 1
  11. 2025MedCalc-Eval and MedCalc-Env: Advancing Medical Calculation Capabilities of Large Language Modelscited by 0
  12. 2026From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environmentscited by 0
2 more
  1. 2026Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Modelscited by 0
  2. 2026GLoC-EHR: Evidence-Cited Clinical Reasoning over Global Context and Local EHR Eventscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Toward Better EHR Reasoning in LLMs: Reinforcement Learning with Expert Attention Guidance
  2. 2025Reasoning LLMs in the Medical Domain: A Literature Survey
  3. 2026Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach
  4. 2025Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications
  5. 2026GraphWalker: Patient Analogy Meets Information Gain for Clinical Reasoning with Large Language Models
  6. 2025MedVLThinker: Simple Baselines for Multimodal Medical Reasoning
  7. 2025Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL
  8. 2024LLMs-based Few-Shot Disease Predictions using EHR: A Novel Approach Combining Predictive Agent Reasoning and Critical Agent Instruction