# Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning

arXiv: https://arxiv.org/abs/2505.19213 · HTML: https://mlsanity.com/paper/2505.19213/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 25 May 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 25 of 25)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [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)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization](https://mlsanity.com/paper/2503.12937/) (2025)
- [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025)
- [Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization](https://mlsanity.com/paper/2311.16839/) (2023)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale](https://mlsanity.com/paper/2406.19280/) (2024)
- [Aligning Modalities in Vision Large Language Models via Preference Fine-tuning](https://mlsanity.com/paper/2402.11411/) (2024)
- [Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data](https://mlsanity.com/paper/2308.02463/) (2023)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2503.13939/) (2025)
- [VisualPRM: An Effective Process Reward Model for Multimodal Reasoning](https://mlsanity.com/paper/2503.10291/) (2025)
- [RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness](https://mlsanity.com/paper/2405.17220/) (2024)
- [MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs](https://mlsanity.com/paper/2504.00993/) (2025)
- [Virgo: A Preliminary Exploration on Reproducing o1-like MLLM](https://mlsanity.com/paper/2501.01904/) (2025)
- [FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training](https://mlsanity.com/paper/2501.09213/) (2025)

## Built on by (most cited first, 16 of 16)

- [Think Twice to See More: Iterative Visual Reasoning in Medical VLMs](https://mlsanity.com/paper/2510.10052/) (2025)
- [Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning](https://mlsanity.com/paper/2508.16129/) (2025)
- [MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning](https://mlsanity.com/paper/2604.08203/) (2026)
- [Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation](https://mlsanity.com/paper/2508.12957/) (2025)
- [Skin-R1: Clinical Knowledge-Guided Dermatological Diagnosis Using Vision-Language Models](https://mlsanity.com/paper/2511.14900/) (2025)
- [CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learning](https://mlsanity.com/paper/2508.03733/) (2025)
- [AdaThink-Med: Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty Quantification](https://mlsanity.com/paper/2509.24560/) (2025)
- [Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models](https://mlsanity.com/paper/2510.18303/) (2025)
- [ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging](https://mlsanity.com/paper/2601.05560/) (2026)
- [Incentivizing Cardiologist-Like Reasoning in MLLMs for Interpretable Echocardiographic Diagnosis](https://mlsanity.com/paper/2601.08440/) (2026)
- [A global log for medical AI](https://mlsanity.com/paper/2510.04033/) (2025)
- [A Vision for Multisensory Intelligence: Sensing, Science, and Synergy](https://mlsanity.com/paper/2601.04563/) (2026)
- [MedLoc-R1: Performance-Aware Curriculum Reward Scheduling for GRPO-Based Medical Visual Grounding](https://mlsanity.com/paper/2603.28120/) (2026)
- [Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming](https://mlsanity.com/paper/2605.21652/) (2026)
- [Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning](https://mlsanity.com/paper/2606.31599/) (2026)
- [CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models](https://mlsanity.com/paper/2608.26147/) (2026)

## Abstract (arXiv)

Recent advances in reinforcement learning with verifiable, rule-based rewards have greatly enhanced the reasoning capabilities and out-of-distribution generalization of VLMs/LLMs, obviating the need for manually crafted reasoning chains. Despite these promising developments in the general domain, their translation to medical imaging remains limited. Current medical reinforcement fine-tuning (RFT) methods predominantly focus on close-ended VQA, thereby restricting the model's ability to engage in world knowledge retrieval and flexible task adaptation. More critically, these methods fall short of addressing the critical clinical demand for open-ended, reasoning-intensive decision-making. To bridge this gap, we introduce MedCCO, the first multimodal reinforcement learning framework tailored for medical VQA that unifies close-ended and open-ended data within a curriculum-driven RFT paradigm. Specifically, MedCCO is initially fine-tuned on a diverse set of close-ended medical VQA tasks to establish domain-grounded reasoning capabilities, and is then progressively adapted to open-ended tasks to foster deeper knowledge enhancement and clinical interpretability. We validate MedCCO across eight challenging medical VQA benchmarks, spanning both close-ended and open-ended settings. Experimental results show that MedCCO consistently enhances performance and generalization, achieving a 11.4% accuracy gain across three in-domain tasks, and a 5.7% improvement on five out-of-domain benchmarks. These findings highlight the promise of curriculum-guided RL in advancing robust, clinically-relevant reasoning in medical multimodal language models.