# VTool-R1
Model weights for the paper "VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use"


[![Paper](https://img.shields.io/badge/paper-5f16a8?style=for-the-badge&logo=arxiv&logoColor=white&color=FF5F05)](https://arxiv.org/pdf/2505.19255)
[![HOMEPAGE](https://img.shields.io/badge/HOMEPAGE-3858bf?style=for-the-badge&logo=homepage&logoColor=white&color=13294B)](https://vtool-r1.github.io/)
[![Weights](https://img.shields.io/badge/Model%20Weights-63cad3?style=for-the-badge&logo=huggingface&logoColor=white&color=FF5F05)](https://huggingface.co/VTOOL)

[Chart 3B](https://huggingface.co/VTOOL/VTOOL-R1-3B-V3-F)

[Chart 7B](https://huggingface.co/VTOOL/VTOOL-R1-7B-F)

[Chart 32B](https://huggingface.co/VTOOL/VTOOL-R1-32B-F)

We are working on training better versions of our Table models, they will be available very soon.

[Table 3B (Soon)]()

[Table 7B (Soon)]()

[Table 32B (Soon)]()

If you find our project helpful, please cite:

<pre style="background-color: auto; padding: 0.8rem 1rem 0.4rem 1rem; border-radius: 8px; overflow-x: auto; font-size: 0.9rem;">
@misc{wu2025vtoolr1vlmslearnthink,
      title={VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use}, 
      author={Mingyuan Wu and Jingcheng Yang and Jize Jiang and Meitang Li and Kaizhuo Yan and Hanchao Yu and Minjia Zhang and Chengxiang Zhai and Klara Nahrstedt},
      year={2025},
      eprint={2505.19255},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2505.19255}, 
}