Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.16189 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910055993966592 |
|---|---|
| author | Wang, Haomin Wei, Qi Ma, Qianli Ding, Shengyuan Yin, Jinhui Chen, Kai Zhang, Hongjie |
| author_facet | Wang, Haomin Wei, Qi Ma, Qianli Ding, Shengyuan Yin, Jinhui Chen, Kai Zhang, Hongjie |
| contents | With the rapid advancement of vision-language models, an increasing number of studies have explored their potential for SVG generation tasks. Although existing approaches improve performance by constructing large-scale SVG datasets and introducing SVG-specific tokens, they still suffer from limited generalization, redundant paths in code outputs, and a lack of explicit reasoning. In this work, we present CTRL-S (Chain-of-Thought Reinforcement Learning for SVG), a unified framework that introduces a chain-of-thought mechanism to explicitly expose the model's reasoning process during SVG generation. To support this structured reasoning, we construct SVG-Sophia, a high-quality dataset containing 145K samples across SVG code refinement, Text-to-SVG, and Image-to-SVG tasks. By training the model to generate group-level structured SVG code, CTRL-S significantly improves structural coherence and visual fidelity. Furthermore, we adopt the GRPO algorithm and design a multi-reward optimization framework, incorporating DINO, image-text similarity, format, and code efficiency rewards. Through joint multi-reward optimization and multi-task training, our approach systematically enhances overall generation capabilities. Extensive experiments show that CTRL-S outperforms existing methods, achieving higher task success rates, superior SVG code quality, and exceptional visual fidelity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16189 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning Wang, Haomin Wei, Qi Ma, Qianli Ding, Shengyuan Yin, Jinhui Chen, Kai Zhang, Hongjie Computer Vision and Pattern Recognition With the rapid advancement of vision-language models, an increasing number of studies have explored their potential for SVG generation tasks. Although existing approaches improve performance by constructing large-scale SVG datasets and introducing SVG-specific tokens, they still suffer from limited generalization, redundant paths in code outputs, and a lack of explicit reasoning. In this work, we present CTRL-S (Chain-of-Thought Reinforcement Learning for SVG), a unified framework that introduces a chain-of-thought mechanism to explicitly expose the model's reasoning process during SVG generation. To support this structured reasoning, we construct SVG-Sophia, a high-quality dataset containing 145K samples across SVG code refinement, Text-to-SVG, and Image-to-SVG tasks. By training the model to generate group-level structured SVG code, CTRL-S significantly improves structural coherence and visual fidelity. Furthermore, we adopt the GRPO algorithm and design a multi-reward optimization framework, incorporating DINO, image-text similarity, format, and code efficiency rewards. Through joint multi-reward optimization and multi-task training, our approach systematically enhances overall generation capabilities. Extensive experiments show that CTRL-S outperforms existing methods, achieving higher task success rates, superior SVG code quality, and exceptional visual fidelity. |
| title | Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.16189 |