This is
PyVision-Image-7B-RL, a multimodal agentic vision model post-trained from
Qwen2.5-VL-7B-Instruct using the PyVision-RL reinforcement learning framework.
Reinforcement learning for agentic multimodal models often suffers from "interaction collapse," where models learn to reduce tool usage and multi-turn reasoning. PyVision-RL is a framework designed to stabilize training and sustain interaction using an oversampling-filtering-ranking rollout strategy combined with an accumulative tool reward.
PyVision-Image-7B-RL is specifically optimized for image understanding tasks and sustained multi-turn tool interaction, demonstrating strong performance and efficiency for scalable multimodal agents.
1@article{pyvisionrl2026,
2 title={PyVision-RL: Forging Open Agentic Vision Models via RL},
3 author={Zhao, Shitian and Lin, Shaoheng and Li, Ming and Zhang, Haoquan and Peng, Wenshuo and Zhang, Kaipeng and Wei, Chen},
4 journal={arXiv:2602.20739},
5 year={2026}
6}
