# DiagR1: A Vision-Language Model Trained via Reinforcement Learning for Digestive Pathology Diagnosis

arXiv: https://arxiv.org/abs/2507.18433 · HTML: https://mlsanity.com/paper/2507.18433/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 20 of its 49 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Multimodal Whole Slide Foundation Model for Pathology](https://mlsanity.com/paper/2411.19666/) (2024)
- [LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs](https://mlsanity.com/paper/2501.06186/) (2025)
- [Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2503.13939/) (2025)
- [Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos](https://mlsanity.com/paper/2312.04746/) (2023)
- [A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model](https://mlsanity.com/paper/2407.15362/) (2024)
- [PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of Pathology](https://mlsanity.com/paper/2305.15072/) (2023)
- [HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interaction](https://mlsanity.com/paper/2403.05396/) (2024)
- [Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation](https://mlsanity.com/paper/2407.18449/) (2024)
- [Dual Attention Model with Reinforcement Learning for Classification of Histology Whole-Slide Images](https://mlsanity.com/paper/2302.09682/) (2023)
- [HistoGym: A Reinforcement Learning Environment for Histopathological Image Analysis](https://mlsanity.com/paper/2408.08847/) (2024)

## Abstract (arXiv)

Multimodal large models have shown great potential in automating pathology image analysis. However, current multimodal models for gastrointestinal pathology are constrained by both data quality and reasoning transparency: pervasive noise and incomplete annotations in public datasets predispose vision language models to factual hallucinations when generating diagnostic text, while the absence of explicit intermediate reasoning chains renders the outputs difficult to audit and thus less trustworthy in clinical practice. To address these issues, we construct a large scale gastrointestinal pathology dataset containing both microscopic descriptions and diagnostic conclusions, and propose a prompt argumentation strategy that incorporates lesion classification and anatomical site information. This design guides the model to better capture image specific features and maintain semantic consistency in generation. Furthermore, we employ a post training pipeline that combines supervised fine tuning with Group Relative Policy Optimization (GRPO) to improve reasoning quality and output structure. Experimental results on real world pathology report generation tasks demonstrate that our approach significantly outperforms state of the art open source and proprietary baselines in terms of generation quality, structural completeness, and clinical relevance. Our solution outperforms state of the art models with 18.7% higher clinical relevance, 32.4% improved structural completeness, and 41.2% fewer diagnostic errors, demonstrating superior accuracy and clinical utility compared to existing solutions.