# Figures as Programs: Recursive Generation of Editable Scientific Figures

arXiv: https://arxiv.org/abs/2609.01006 · HTML: https://mlsanity.com/paper/2609.01006/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [StarVector: Generating Scalable Vector Graphics Code from Images and Text](https://mlsanity.com/paper/2312.11556/) (2023)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ](https://mlsanity.com/paper/2310.00367/) (2023)
- [OmniSVG: A Unified Scalable Vector Graphics Generation Model](https://mlsanity.com/paper/2504.06263/) (2025)
- [ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language](https://mlsanity.com/paper/2311.01920/) (2023)
- [AutoPresent: Designing Structured Visuals from Scratch](https://mlsanity.com/paper/2501.00912/) (2025)
- [Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers](https://mlsanity.com/paper/2505.21497/) (2025)
- [AI4Research: A Survey of Artificial Intelligence for Scientific Research](https://mlsanity.com/paper/2507.01903/) (2025)
- [Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models](https://mlsanity.com/paper/2411.16602/) (2024)
- [Qwen-Image-2.0 Technical Report](https://mlsanity.com/paper/2605.10730/) (2026)
- [Towards Execution-Grounded Automated AI Research](https://mlsanity.com/paper/2601.14525/) (2026)
- [MARS: Modular Agent with Reflective Search for Automated AI Research](https://mlsanity.com/paper/2602.02660/) (2026)
- [AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations](https://mlsanity.com/paper/2602.03828/) (2026)
- [ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?](https://mlsanity.com/paper/2412.02368/) (2024)
- [Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations](https://mlsanity.com/paper/2510.05571/) (2025)
- [Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs](https://mlsanity.com/paper/2605.30611/) (2026)
- [Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration](https://mlsanity.com/paper/2603.29590/) (2026)
- [ConvexBench: Can LLMs Recognize Convex Functions?](https://mlsanity.com/paper/2602.01075/) (2026)

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

- [FigAct: Turning Scientific Figures into Active Canvases for Explanation](https://mlsanity.com/paper/2609.36190/) (2026)
- [One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline](https://mlsanity.com/paper/2610.06852/) (2026)

## Abstract (arXiv)

Scientific methodology figures are essential for communicating complex methods clearly, yet creating them remains labor-intensive and typically requires multiple rounds of refinement. Recent image-generation models can synthesize visually appealing raster figures, but producing a human-satisfactory result in a single generation step remains difficult. Moreover, precise edits to raster figures are challenging for both humans and models. We formulate scientific figure generation as recursive SVG program construction and propose textscFigTree, a textitmulti-agent system that automatically transforms a scientific paper into a structured vector figure. textscFigTree grounds figure content in the source paper, decomposes a figure into a hierarchy of local regions, generates each region as a short SVG program, and assembles the resulting fragments. A render-critic refinement loop jointly inspects the rendered figure and its underlying program, enabling visual defects to be traced to specific statements and accurately repaired. We conduct extensive evaluations of textscFigTree on figure quality and editability, showing that textscFigTree produces high-quality figures, while also enabling more effective editing than existing raster-based methods.