# EditGRPO: Reinforcement Learning with Post-Rollout Edits for Clinically Accurate Chest X-Ray Report Generation

arXiv: https://arxiv.org/abs/2509.22812 · HTML: https://mlsanity.com/paper/2509.22812/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Deep reinforcement learning methods / [RL for clinical treatment and surgery](https://mlsanity.com/deeprl/rl-for-clinical-treatment-and-surgery/)

## Builds on (most cited first, 19 of 19)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT](https://mlsanity.com/paper/2004.09167/) (2020)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation](https://mlsanity.com/paper/2010.10042/) (2020)
- [Clinically Accurate Chest X-Ray Report Generation](https://mlsanity.com/paper/1904.02633/) (2019)
- [MedVersa: A Generalist Foundation Model for Medical Image Interpretation](https://mlsanity.com/paper/2405.07988/) (2024)
- [ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification](https://mlsanity.com/paper/2504.20930/) (2025)
- [X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains](https://mlsanity.com/paper/2505.03981/) (2025)
- [ReXGradient-160K: A Large-Scale Publicly Available Dataset of Chest Radiographs with Free-text Reports](https://mlsanity.com/paper/2505.00228/) (2025)
- [Multimodal Large Language Model driven Radiology Report Generation with Clinical Knowledge Enhancement](https://mlsanity.com/paper/2403.06728/) (2024)

## Built on by (most cited first, 4 of 4)

- [MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine](https://mlsanity.com/paper/2603.00842/) (2026)
- [Rethinking the Efficiency and Effectiveness of Reinforcement Learning for Radiology Report Generation](https://mlsanity.com/paper/2603.04022/) (2026)
- [Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation](https://mlsanity.com/paper/2608.05341/) (2026)
- [From Sampled Evidence to Radiology Reports: Objectives, Constraints, and Realization](https://mlsanity.com/paper/2610.17318/) (2026)

## Abstract (arXiv)

Radiology report generation requires advanced medical image analysis, effective temporal reasoning, and accurate text generation. Although recent innovations, particularly multimodal large language models, have shown improved performance, their supervised fine-tuning (SFT) objective is not explicitly aligned with clinical efficacy. In this work, we introduce EditGRPO, a mixed-policy reinforcement learning algorithm designed specifically to optimize the generation through clinically motivated rewards. EditGRPO integrates on-policy exploration with off-policy guidance by injecting sentence-level detailed corrections during training rollouts. This mixed-policy approach addresses the exploration dilemma and sampling efficiency issues typically encountered in RL. Applied to a Qwen2.5-VL-3B, EditGRPO outperforms both SFT and vanilla GRPO baselines, achieving an average improvement of 3.4% in clinical metrics across four major datasets. Notably, EditGRPO also demonstrates superior out-of-domain generalization, with an average performance gain of 5.9% on unseen datasets.