Saint-lsy/MedSAM-Agent-Qwen3-VL-8B-MedSAM2

MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning

🤖 **Model** | **📖 Paper** | **💻 Code**

MedSAM-Agent is a framework that reformulates interactive medical image segmentation as a multi-step autonomous decision-making process. It leverages Multi-modal Large Language Models (MLLMs) as autonomous agents, employing reinforcement learning with verifiable reward (RLVR) to orchestrate specialized tools like the Segment Anything Model (SAM).

Overview

Medical image segmentation is evolving from task-specific models toward generalizable frameworks. MedSAM-Agent introduces:

• —Hybrid Prompting Strategy: Enables the model to internalize human-like decision heuristics and adaptive refinement strategies.
• —Two-stage Training Pipeline: Integrates multi-turn, end-to-end outcome verification with a clinical-fidelity process reward design.

Sample Usage

To run inference on a single medical image sample, you can use the provided script from the official repository:

cd infer
python run_single_inference.py \
  --img-path infer/demo/BTCV-0-106_CT_abdomen.png \
  --target-description "right kidney in abdomen CT" \
  --model-path /path/to/mllm_model \
  --seg-checkpoint /path/to/MedSAM2_latest.pt \
  --seg-model medsam

Citation

If you find this work helpful for your project, please consider citing the paper:

@misc{liu2026medsamagentempoweringinteractivemedical,
      title={MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning}, 
      author={Shengyuan Liu and Liuxin Bao and Qi Yang and Wanting Geng and Boyun Zheng and Chenxin Li and Wenting Chen and Houwen Peng and Yixuan Yuan},
      year={2026},
      eprint={2602.03320},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2602.03320}, 
}