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

[2505.24499] Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2505.24499 (cs) [Submitted on 30 May 2025 ( v1 ), last revised 9 Apr 2026 (this version, v2)] Title: Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning Authors: Ximing Xing , Ziteng Xue , Yandong Guan , Jing Zhang , Dong Xu , Qian Yu View a PDF of the paper titled Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning, by Ximing Xing and 5 other authors View PDF HTML (experimental) 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. Comments: Accepted by CVPR 2026. 16 pages, 7 figures Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2505.24499 [cs.CV] (or arXiv:2505.24499v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2505.24499 Focus to learn more arXiv-issued DOI via DataCite Submission history From: XiMing Xing [ view email ] [v1] Fri, 30 May 2025 11:57:58 UTC (2,643 KB) [v2] Thu, 9 Apr 2026 03:43:40 UTC (6,153 KB) Full-text links: Access Paper: View a PDF of the paper titled Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning, by Ximing Xing and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2025-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning#618605
• OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation#182756
• SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward#447979
• ReSolve: Reusing Candidate Reasoning through Selective Generative Moderation#1156075
• Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls#394464