VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910039141253120 |
|---|---|
| author | Lai, Jinxiang Lu, Zexin He, Jiajun Quan, Rongwei Zhao, Wenzhe Yang, Qinyu Chen, Qi Lin, Qin Li, Chuyue Gao, Tao Shan, Yuhao Shao, Shuai Guo, Song Lu, Qinglin |
| author_facet | Lai, Jinxiang Lu, Zexin He, Jiajun Quan, Rongwei Zhao, Wenzhe Yang, Qinyu Chen, Qi Lin, Qin Li, Chuyue Gao, Tao Shan, Yuhao Shao, Shuai Guo, Song Lu, Qinglin |
| contents | Visual content creation tasks demand a nuanced understanding of design conventions and creative workflows-capabilities challenging for general models, while workflow-based agents lack specialized knowledge for autonomous creative planning. To overcome these challenges, we propose VisionCreator, a native visual-generation agentic model that unifies Understanding, Thinking, Planning, and Creation (UTPC) capabilities within an end-to-end learnable framework. Our work introduces four key contributions: (i) VisGenData-4k and its construction methodology using metacognition-based VisionAgent to generate high-quality creation trajectories with explicit UTPC structures; (ii) The VisionCreator agentic model, optimized through Progressive Specialization Training (PST) and Virtual Reinforcement Learning (VRL) within a high-fidelity simulated environment, enabling stable and efficient acquisition of UTPC capabilities for complex creation tasks; (iii) VisGenBench, a comprehensive benchmark featuring 1.2k test samples across diverse scenarios for standardized evaluation of multi-step visual creation capabilities; (iv) Remarkably, our VisionCreator-8B/32B models demonstrate superior performance over larger closed-source models across multiple evaluation dimensions. Overall, this work provides a foundation for future research in visual-generation agentic systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02681 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creation Lai, Jinxiang Lu, Zexin He, Jiajun Quan, Rongwei Zhao, Wenzhe Yang, Qinyu Chen, Qi Lin, Qin Li, Chuyue Gao, Tao Shan, Yuhao Shao, Shuai Guo, Song Lu, Qinglin Computer Vision and Pattern Recognition Visual content creation tasks demand a nuanced understanding of design conventions and creative workflows-capabilities challenging for general models, while workflow-based agents lack specialized knowledge for autonomous creative planning. To overcome these challenges, we propose VisionCreator, a native visual-generation agentic model that unifies Understanding, Thinking, Planning, and Creation (UTPC) capabilities within an end-to-end learnable framework. Our work introduces four key contributions: (i) VisGenData-4k and its construction methodology using metacognition-based VisionAgent to generate high-quality creation trajectories with explicit UTPC structures; (ii) The VisionCreator agentic model, optimized through Progressive Specialization Training (PST) and Virtual Reinforcement Learning (VRL) within a high-fidelity simulated environment, enabling stable and efficient acquisition of UTPC capabilities for complex creation tasks; (iii) VisGenBench, a comprehensive benchmark featuring 1.2k test samples across diverse scenarios for standardized evaluation of multi-step visual creation capabilities; (iv) Remarkably, our VisionCreator-8B/32B models demonstrate superior performance over larger closed-source models across multiple evaluation dimensions. Overall, this work provides a foundation for future research in visual-generation agentic systems. |
| title | VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.02681 |