# Rendering-Aware Reinforcement Learning for Vector Graphics Generation

arXiv: https://arxiv.org/abs/2505.20793 · HTML: https://mlsanity.com/paper/2505.20793/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2025.

## Built on by (most cited first, 30 of 39)

- [VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning](https://mlsanity.com/paper/2511.00391/) (2025)
- [Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation](https://mlsanity.com/paper/2508.13587/) (2025)
- [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)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation](https://mlsanity.com/paper/2602.05998/) (2026)
- [DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance](https://mlsanity.com/paper/2512.10894/) (2025)
- [Symbolic Graphics Programming with Large Language Models](https://mlsanity.com/paper/2509.05208/) (2025)
- [VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation](https://mlsanity.com/paper/2605.01517/) (2026)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing](https://mlsanity.com/paper/2603.29852/) (2026)
- [IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework](https://mlsanity.com/paper/2603.09312/) (2026)
- [VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models](https://mlsanity.com/paper/2603.24575/) (2026)
- [OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward](https://mlsanity.com/paper/2604.05514/) (2026)
- [SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis](https://mlsanity.com/paper/2602.00249/) (2026)
- [Visual-ERM: Reward Modeling for Visual Equivalence](https://mlsanity.com/paper/2603.13224/) (2026)
- [AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling](https://mlsanity.com/paper/2604.10940/) (2026)
- [GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation](https://mlsanity.com/paper/2605.25447/) (2026)
- [Illustrator's Depth: Monocular Layer Index Prediction for Image Decomposition](https://mlsanity.com/paper/2511.17454/) (2025)
- [Teaching an Agent to Sketch One Part at a Time](https://mlsanity.com/paper/2603.19500/) (2026)
- [Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling](https://mlsanity.com/paper/2604.05072/) (2026)
- [Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis](https://mlsanity.com/paper/2604.08809/) (2026)
- [AnchorFlow: Learning Anchor Placement for Faithful and Editable SVG Reconstruction](https://mlsanity.com/paper/2605.19551/) (2026)
- [Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts](https://mlsanity.com/paper/2606.10334/) (2026)
- [SciForma: Structure-Faithful Generation of Scientific Diagrams](https://mlsanity.com/paper/2607.18091/) (2026)
- [EdiTikZ: Scientific Figure Editing from Revision Trajectories](https://mlsanity.com/paper/2609.01409/) (2026)
- [Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts](https://mlsanity.com/paper/2609.35641/) (2026)
- [Understanding Virality: A Rubric based Vision-Language Model Framework for Short-Form Edutainment Evaluation](https://mlsanity.com/paper/2512.21402/) (2025)
- [From Tokens to Numbers: Continuous Number Modeling for SVG Generation](https://mlsanity.com/paper/2602.02820/) (2026)
- [Decomposer: Learning to Decompile Symbolic Music to Programs](https://mlsanity.com/paper/2607.01849/) (2026)

## Abstract (arXiv)

Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in vision-language models (VLMs) have enabled high-quality SVG generation by framing the problem as a code generation task and leveraging large-scale pretraining. VLMs are particularly suitable for this task as they capture both global semantics and fine-grained visual patterns, while transferring knowledge across vision, natural language, and code domains. However, existing VLM approaches often struggle to produce faithful and efficient SVGs because they never observe the rendered images during training. Although differentiable rendering for autoregressive SVG code generation remains unavailable, rendered outputs can still be compared to original inputs, enabling evaluative feedback suitable for reinforcement learning (RL). We introduce RLRF (Reinforcement Learning from Rendering Feedback), an RL method that enhances SVG generation in autoregressive VLMs by leveraging feedback from rendered SVG outputs. Given an input image, the model generates SVG roll-outs that are rendered and compared to the original image to compute a reward. This visual fidelity feedback guides the model toward producing more accurate, efficient, and semantically coherent SVGs. RLRF significantly outperforms supervised fine-tuning, addressing common failure modes and enabling precise, high-quality SVG generation with strong structural understanding and generalization.