paper-with-me

홈 › Papers

Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning

2026-03-17 · Haomin Wang, Qi Wei, Qianli Ma, Shengyuan Ding, Jinhui Yin, Kai Chen, Hongjie Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.16189

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration

2024-10-03 · Weikang Yuan, Junjie Cao, Zhuoren Jiang, Yangyang Kang 외

Large Language Models (LLMs) could struggle to fully understand legal theories and perform complex legal reasoning tasks. In this study, we introduce a challenging task (confusing charge prediction) to better evaluate LL…

Legal Reasoning

M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding

2026-01-13 · Juntao Jiang, Jiangning Zhang, Yali Bi, Jinsheng Bai 외 arxiv

Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by encouraging step-by-step intermediate reasoning, and recent advances have extended this paradigm to Multimodal Large Language Mo…

Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs

2026-02-09 · Siqu Ou, Tianrui Wan, Zhiyuan Zhao, Junyu Gao 외 arxiv

While chain-of-thought (CoT) reasoning has substantially improved multimodal large language models (MLLMs) on complex reasoning tasks, existing approaches largely rely on long textual reasoning trajectories and provide l…

Reinforcement LearningVisual Reasoning

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought

2025-01-13 · Chengzu Li, Wenshan Wu, Huanyu Zhang, Yan Xia 외

Chain-of-Thought (CoT) prompting has proven highly effective for enhancing complex reasoning in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Yet, it struggles in complex spatial reasoning ta…

Spatial Reasoning

Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning

2025-07-01 · Bob Zhang, Haoran Li, Tao Zhang, Jianan Li 외 arxiv

Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instructions. To address this, we adopt a reinfo…

Reinforcement LearningVisual Grounding