mlsanityData to 7 Oct 2026

ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification

arXiv 2504.20930 ↗First posted 29 Apr 2025cs.AI cs.CL cs.CVcited by 30

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

Recent advances in reasoning-enhanced large language models (LLMs) and multimodal LLMs (MLLMs) have significantly improved performance in complex tasks, yet medical AI models often overlook the structured reasoning processes inherent in clinical practice. In this work, we present ChestX-Reasoner, a radiology diagnosis MLLM designed to leverage process supervision mined directly from clinical reports, reflecting the step-by-step reasoning followed by radiologists. We construct a large dataset by extracting and refining reasoning chains from routine radiology reports. Our two-stage training framework combines supervised fine-tuning and reinforcement learning guided by process rewards to better align model reasoning with clinical standards. We introduce RadRBench-CXR, a comprehensive benchmark featuring 59K visual question answering samples with 301K clinically validated reasoning steps, and propose RadRScore, a metric evaluating reasoning factuality, completeness, and effectiveness. ChestX-Reasoner outperforms existing medical and general-domain MLLMs in both diagnostic accuracy and reasoning ability, achieving 16%, 5.9%, and 18% improvements in reasoning ability compared to the best medical MLLM, the best general MLLM, and its base model, respectively, as well as 3.3%, 24%, and 27% improvements in outcome accuracy. All resources are open-sourced to facilitate further research in medical reasoning MLLMs.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 19 of its 41 references that are in the map. First posted on arXiv 29 Apr 2025.

Builds on

19 of 41 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models18 Mar
  2. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning26 Feb
  3. 2024HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs25 Dec

Other references · 16

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  4. 2024GPT-4o System Cardcited by 4,467
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  6. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  7. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 641
  8. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 590
  9. 2025MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understandingcited by 212
  10. 2023Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Datacited by 176
  11. 2025R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Modelcited by 163
  12. 2025AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoningcited by 108
4 more
  1. 2024VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selectioncited by 64
  2. 2024Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoningcited by 50
  3. 2025Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systemscited by 49
  4. 2025VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Modelscited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 18; 2026: 12.

30 papers.

Sort:

By area:

  1. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  2. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  3. 2025Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Modelscited by 43
  4. 2025Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Searchcited by 16
  5. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Modelscited by 13
  6. 2025Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applicationscited by 10
  7. 2025Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbationscited by 9
  8. 2025Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoningcited by 8
  9. 2025Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoningcited by 6
  10. 20253DReasonKnee: Advancing Grounded Reasoning in Medical Vision Language Modelscited by 5
  11. 2025Training and Evaluation of Guideline-Based Medical Reasoning in LLMscited by 4
  12. 2025Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learningcited by 4
18 more
  1. 2026A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretationcited by 4
  2. 2025EditGRPO: Reinforcement Learning with Post-Rollout Edits for Clinically Accurate Chest X-Ray Report Generationcited by 3
  3. 2025CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learningcited by 2
  4. 2026When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gainscited by 2
  5. 2026Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reportscited by 2
  6. 2025MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMscited by 1
  7. 2025Teaching AI Stepwise Diagnostic Reasoning with Report-Guided Chain-of-Thought Learningcited by 1
  8. 2026GAZE: Grounded Agentic Zero-shot Evaluation with Viewer-Level Tools and Literature Retrieval on Rare Brain MRIcited by 1
  9. 2026Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoningcited by 1
  10. 2026Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoningcited by 1
  11. 2026The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomycited by 1
  12. 2025Adapting and Evaluating Multimodal Large Language Models for Adolescent Idiopathic Scoliosis Self-Management: A Divide and Conquer Frameworkcited by 0
  13. 2025Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patientscited by 0
  14. 2026PhenoLIP: Integrating Phenotype Ontology Knowledge into Medical Vision-Language Pretrainingcited by 0
  15. 2026EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Modelscited by 0
  16. 2026Positive-Unlabeled Preference Optimization For Chest X-ray Report Generationcited by 0
  17. 2026UR2-MLLM: Uncertainty-aware Revisit Reasoning in Multimodal Large Language Models for Radiology Report Generationcited by 0
  18. 2026Enhancing Visual Reasoning in Chest X-Ray Report Generation Using Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning Visual Language Model for Chest X-Ray Analysis
  2. 2025Toward Clinically Explainable AI for Medical Diagnosis: A Foundation Model with Human-Compatible Reasoning via Reinforcement Learning
  3. 2025CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays
  4. 2026CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs
  5. 2025Interpreting Chest X-rays Like a Radiologist: A Benchmark with Clinical Reasoning
  6. 2026HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize
  7. 2026MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rays
  8. 2025Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation