Figures as Programs: Recursive Generation of Editable Scientific Figures

arXiv:2609.01006 · cs.AI, cs.GR · Submitted 2026-09-01 · Read on arXiv

cs.AI, cs.GR

Submitted: 2026-09-01

Updated: 2026-09-01

Code: https://github.com/yepengliu/FigTree

License: http://creativecommons.org/licenses/by-sa/4.0/

The gist: Scientific methodology figures are essential for communicating complex methods clearly, yet creating them remains labor-intensive and typically requires multiple rounds of refinement.

Terminology

Abstract

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 FigTree, a multi-agent system that automatically transforms a scientific paper into a structured vector figure. FigTree 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 FigTree on figure quality and editability, showing that FigTree produces high-quality figures, while also enabling more effective editing than existing raster-based methods.

Sources

Related papers