# GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation

arXiv: https://arxiv.org/abs/2605.25447 · HTML: https://mlsanity.com/paper/2605.25447/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 17 of its 19 references that are in the map.
- First posted on arXiv 25 May 2026.

## Placed in

- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 17 of 17)

- [StarVector: Generating Scalable Vector Graphics Code from Images and Text](https://mlsanity.com/paper/2312.11556/) (2023)
- [OmniSVG: A Unified Scalable Vector Graphics Generation Model](https://mlsanity.com/paper/2504.06263/) (2025)
- [Empowering LLMs to Understand and Generate Complex Vector Graphics](https://mlsanity.com/paper/2412.11102/) (2024)
- [Rendering-Aware Reinforcement Learning for Vector Graphics Generation](https://mlsanity.com/paper/2505.20793/) (2025)
- [SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities](https://mlsanity.com/paper/2404.13710/) (2024)
- [AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations](https://mlsanity.com/paper/2602.03828/) (2026)
- [SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation](https://mlsanity.com/paper/2506.03139/) (2025)
- [UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models](https://mlsanity.com/paper/2508.07766/) (2025)
- [SVGen: Interpretable Vector Graphics Generation with Large Language Models](https://mlsanity.com/paper/2508.09168/) (2025)
- [AutoFigure-Edit: Generating Editable Scientific Illustration](https://mlsanity.com/paper/2603.06674/) (2026)
- [DiagramEval: Evaluating LLM-Generated Diagrams via Graphs](https://mlsanity.com/paper/2510.25761/) (2025)
- [Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning](https://mlsanity.com/paper/2603.16189/) (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)
- [TechING: Towards Real World Technical Image Understanding via VLMs](https://mlsanity.com/paper/2601.18238/) (2026)
- [Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis](https://mlsanity.com/paper/2604.08809/) (2026)

## Built on by (most cited first, 2 of 2)

- [Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts](https://mlsanity.com/paper/2609.35641/) (2026)
- [CommerceVibe: Learning to Design E-Commerce Creatives as Executable Visual Code via Dual-Feedback Reinforcement Learning](https://mlsanity.com/paper/2608.27893/) (2026)

## Abstract (arXiv)

Generating structured, editable diagrams remains a significant challenge for contemporary large language models, despite their proficiency in general-purpose vector code generation. The primary difficulty lies in the structural fragility of the output; minor errors such as misaligned connector endpoints, text labels overlapping borders, or complex layouts drifting beyond the canvas boundaries render the resulting SVG files functionally unusable for professional applications. To address these issues, we introduce GeoSVG-RL, a specialized reinforcement learning framework designed for layout-constrained text-to-SVG generation. Unlike standard training objectives that rely solely on maximizing token-level likelihood, our approach optimizes the policy against explicit, executable geometric feedback. The model first produces a structured layout plan that serves as a geometric contract for the subsequent generation of the SVG code. This code is then rendered through a browser-backed verifier, enabling the calculation of fine-grained rewards across six critical dimensions: rendering validity, canvas fitting, precise anchor placement, text containment, graph consistency, and code cleanliness. We utilize Group Relative Policy Optimization (GRPO) to refine the model, sampling multiple candidates per prompt to facilitate updates based on relative quality. Starting from a supervised warm-start phase on synthetic data, GeoSVG-RL achieves substantial gains in structural reliability, particularly in arrow-anchor accuracy and text-in-box rates. Quantitative evaluations demonstrate that our method consistently outperforms current state-of-the-art systems in local geometric precision and the preservation of graph connectivity, providing a robust pathway toward automated yet reliable technical illustration.