# SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions

arXiv: https://arxiv.org/abs/2607.15272 · HTML: https://mlsanity.com/paper/2607.15272/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026)
- [StarVector: Generating Scalable Vector Graphics Code from Images and Text](https://mlsanity.com/paper/2312.11556/) (2023)
- [Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning](https://mlsanity.com/paper/2508.20751/) (2025)
- [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)
- [SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model](https://mlsanity.com/paper/2505.22126/) (2025)
- [AutoFigure-Edit: Generating Editable Scientific Illustration](https://mlsanity.com/paper/2603.06674/) (2026)

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

- [Pixels or Code? Benchmarking Instruction-Guided Visual Artifact Operation](https://mlsanity.com/paper/2610.16444/) (2026)
- [JevGPT: Thinking Fast and Slow in Autonomous Research](https://mlsanity.com/paper/2610.18272/) (2026)

## Abstract (arXiv)

Editing the figures in a research paper is a routine and time-consuming part of everyday research practice: authors relabel components, rearrange panels, and restyle visuals as they revise their manuscripts. Automating this editing workflow under a natural-language instruction, however, is challenging, because a scientific figure is a dense infographic in which heterogeneous visual elements such as schematics, plots, photos, captions, and arrows are composed under a tight visual grammar to advance a specific argument. To address this, we present SciDiagramEdit, a benchmark and skill-evolution framework that learns from natural paper revisions and operates on the figure's editable vector source, where users can inspect and co-edit individual primitives alongside the agent. Our benchmark mines before/after figure pairs from arXiv version histories, each grounded in the authors' own revision intent. To accommodate the diversity of editing instructions, we adopt agentic learning via skill evolution: an agentic proposer continually refines the agent's skill specification from execution traces over multiple epochs. The resulting skill progressively lifts edit accuracy on a held-out validation set, providing evidence that natural paper revisions are an effective training signal for instruction-driven figure editing.