Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning
This work addresses challenges in SVG generation for applications requiring structured and visually coherent outputs, representing an incremental improvement with novel method integration.
The paper tackles the problem of limited generalization, redundant paths, and lack of explicit reasoning in SVG generation by vision-language models, presenting CTRL-S, a framework that introduces chain-of-thought reasoning and multi-reward optimization, resulting in higher task success rates, superior SVG code quality, and exceptional visual fidelity.
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.