# Med-Evo: Test-time Self-evolution for Medical Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2603.07443 · HTML: https://mlsanity.com/paper/2603.07443/

## 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 23 of its 32 references that are in the map.
- First posted on arXiv 8 Mar 2026.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [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)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [TTRL: Test-Time Reinforcement Learning](https://mlsanity.com/paper/2504.16084/) (2025)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning](https://mlsanity.com/paper/2505.15134/) (2025)
- [LLMs Accelerate Annotation for Medical Information Extraction](https://mlsanity.com/paper/2312.02296/) (2023)
- [First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training](https://mlsanity.com/paper/2505.22453/) (2025)
- [PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging](https://mlsanity.com/paper/2401.02797/) (2024)
- [Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios](https://mlsanity.com/paper/2411.14461/) (2024)
- [TTRV: Test-Time Reinforcement Learning for Vision Language Models](https://mlsanity.com/paper/2510.06783/) (2025)
- [Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback](https://mlsanity.com/paper/2401.05695/) (2024)
- [MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language Models](https://mlsanity.com/paper/2509.23725/) (2025)
- [AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning](https://mlsanity.com/paper/2510.05478/) (2025)
- [Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models](https://mlsanity.com/paper/2505.13973/) (2025)
- [MedGR2: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning](https://mlsanity.com/paper/2508.20549/) (2025)
- [Potential of Multimodal Large Language Models for Data Mining of Medical Images and Free-text Reports](https://mlsanity.com/paper/2407.05758/) (2024)
- [InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoning](https://mlsanity.com/paper/2505.23867/) (2025)
- [CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models](https://mlsanity.com/paper/2511.06430/) (2025)
- [Perceive and Calibrate: Analyzing and Enhancing Robustness of Medical Multi-Modal Large Language Models](https://mlsanity.com/paper/2512.21964/) (2025)
- [Capturing Requirements for a Data Annotation Tool for Intensive Care: Experimental User-Centered Design Study](https://mlsanity.com/paper/2309.16500/) (2023)
- [Federated Few-Shot Learning for Epileptic Seizure Detection Under Privacy Constraints](https://mlsanity.com/paper/2512.13717/) (2025)

## Abstract (arXiv)

Medical Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse healthcare tasks. However, current post-training strategies, such as supervised fine-tuning and reinforcement learning, heavily depend on substantial annotated data while overlooking the potential of unlabeled test data for model enhancement. This limitation becomes particularly pronounced in medical domains, where acquiring extensive labeled medical data is difficult due to the strict data sensitivity and annotation complexity. Moreover, leveraging test data poses challenges in generating reliable supervision signals from unlabeled samples and maintaining stable self-evolution. To address these limitations, we propose Med-Evo, the first self-evolution framework for medical MLLMs that utilizes label-free reinforcement learning to promote model performance without requiring additional labeled data. Our framework introduces two key innovations: 1) Feature-driven Pseudo Labeling (FPL) that identifies semantic centroids from all heterogeneous candidate responses to select pseudo labels in each rollout, and 2) Hard-Soft Reward (HSR) that combines exact match with token-level assessment and semantic similarity to provide hierarchical reward. Experiments on three medical VQA benchmarks and two base MLLMs show clear advantages of our approach over SOTA methods, with significant improvements of 10.43% accuracy and 4.68% recall on the SLAKE dataset using Qwen2.5-VL, showing the effectiveness of our method.