Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning

TL;DR

Reason-SVG introduces a structured reasoning framework with a two-stage training process, combining supervised fine-tuning and reinforcement learning, to enhance the quality and coherence of SVG generation by large language models.

Contribution

It pioneers the 'Drawing-with-Thought' paradigm and develops a hybrid reward function, significantly improving SVG generation accuracy and reasoning capabilities.

Findings

Achieved higher structural validity and semantic accuracy in SVGs.

Demonstrated improved visual coherence in generated SVGs.

Created a new dataset of 10,000 SVG-DwT pairs for training and evaluation.

Abstract

Generating high-quality Scalable Vector Graphics (SVGs) is challenging for Large Language Models (LLMs), as it requires advanced reasoning for structural validity, semantic accuracy, and visual coherence -- areas where current LLMs often struggle. In this work, we introduce Reason-SVG, a novel framework equipped with enhanced structured reasoning for SVG generation. Reason-SVG pioneers the ``Drawing-with-Thought'' (DwT) paradigm, in which models generate both SVG code and explicit design rationales. Reason-SVG follows a two-stage training strategy: First, Supervised Fine-Tuning (SFT) trains the LLM on the DwT paradigm to develop foundational reasoning abilities. Second, Reinforcement Learning (RL), utilizing Group Relative Policy Optimization (GRPO), empowers the model to generate both DwT and SVG rationales through refined, reward-driven reasoning. To enable reasoning-driven SVG generation, we design a Hybrid Reward function that evaluates the presence and effectiveness of DwT reasoning, along with structural validity, semantic alignment, and visual quality. We also introduce the SVGX-DwT-10k dataset, a high-quality corpus of 10k SVG-DwT pairs, where each SVG code is generated based on explicit DwT reasoning. By integrating DwT, SFT, and Hybrid Reward-guided RL, Reason-SVG significantly improves the performance of LLMs and VLMs in generating accurate and visually coherent SVGs.