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

arXiv: https://arxiv.org/abs/2505.24499 · HTML: https://mlsanity.com/paper/2505.24499/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 65 references that are in the map.
- First posted on arXiv 30 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 14 of 14)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models](https://mlsanity.com/paper/2503.20752/) (2025)
- [Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.03318/) (2025)
- [R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning](https://mlsanity.com/paper/2505.02835/) (2025)
- [NeuralSVG: An Implicit Representation for Text-to-Vector Generation](https://mlsanity.com/paper/2501.03992/) (2025)
- [Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation](https://mlsanity.com/paper/2504.09479/) (2025)
- [Beyond Pixels: Exploring Human-Readable SVG Generation for Simple Images with Vision Language Models](https://mlsanity.com/paper/2311.15543/) (2023)
- [SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation](https://mlsanity.com/paper/2412.10437/) (2024)

## Built on by (most cited first, 8 of 8)

- [OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models](https://mlsanity.com/paper/2601.21639/) (2026)
- [Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback](https://mlsanity.com/paper/2604.20730/) (2026)
- [Symbolic Graphics Programming with Large Language Models](https://mlsanity.com/paper/2509.05208/) (2025)
- [Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning](https://mlsanity.com/paper/2603.16189/) (2026)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models](https://mlsanity.com/paper/2603.24575/) (2026)
- [CommerceVibe: Learning to Design E-Commerce Creatives as Executable Visual Code via Dual-Feedback Reinforcement Learning](https://mlsanity.com/paper/2608.27893/) (2026)
- [CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation](https://mlsanity.com/paper/2608.30689/) (2026)

## Abstract (arXiv)

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.