# Enhancing Visual Reasoning in Chest X-Ray Report Generation Using Reinforcement Learning

arXiv: https://arxiv.org/abs/2609.31911 · HTML: https://mlsanity.com/paper/2609.31911/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 18 of 18)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [MAIRA-2: Grounded Radiology Report Generation](https://mlsanity.com/paper/2406.04449/) (2024)
- [CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats](https://mlsanity.com/paper/2405.19538/) (2024)
- [Chest ImaGenome Dataset for Clinical Reasoning](https://mlsanity.com/paper/2108.00316/) (2021)
- [Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.16188/) (2025)
- [ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification](https://mlsanity.com/paper/2504.20930/) (2025)
- [Scaling medical imaging report generation with multimodal reinforcement learning](https://mlsanity.com/paper/2601.17151/) (2026)
- [Toward Clinically Explainable AI for Medical Diagnosis: A Foundation Model with Human-Compatible Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2509.03906/) (2025)
- [Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learning](https://mlsanity.com/paper/2512.10691/) (2025)

## Abstract (arXiv)

Medical report generation has made significant progress with the rise of modern vision-language models and the growing availability of large-scale medical datasets. However, hallucinations remain a major challenge, largely due to the limitations of supervised fine-tuning (SFT), which prioritizes lexical similarity to reference reports rather than clinical correctness. While reinforcement learning has shown strong performance in domains with verifiable rewards such as mathematics and code generation, its application to open-ended medical tasks remains limited. Existing work focuses on evaluating final answers, overlooking the model's reasoning, despite evidence that flawed reasoning can degrade overall performance. In this study, we propose a framework that verifies the model's reasoning process by integrating anatomical regions, bounding boxes, and region-level textual descriptions. We design spatial and factual reward mechanisms to ensure that the model's reasoning is both visually grounded and factually accurate. Starting from Qwen3-VL-8B-Instruct as our base model, we adapt it to the medical domain using supervised fine-tuning, introduce reasoning capability through a cold-start SFT stage, and refine it with reinforcement learning. We find that RL provides performance gains beyond those achievable through SFT alone, and that jointly verifying both reasoning steps and final outputs yields larger improvements than verifying either in isolation. We further identify multiple modes of reward hacking in the RL stage. Finally, the model's structured think traces enhance interpretability, making its outputs easier to audit for clinical use.