Source note2 min read
SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
Source
arXiv
arxiv.org/abs/2607.15272v1
Source
- Source name: arXiv
- Source kind: paper
- Authors / organization: Yasheng Sun, Zezi Zeng, Yifan Yang, Chong Luo, Wenyi Wang, Ziwei Liu, Jürgen Schmidhuber
- Venue: arXiv: cs.CL
- Published: 2026-07-16
- Collected: 2026-07-17
- URL: http://arxiv.org/abs/2607.15272v1
- PDF: https://arxiv.org/pdf/2607.15272v1
- DOI: UNKNOWN
Plain-Language Brief
The paper presents SciDiagramEdit, a system that automates the time-consuming task of editing scientific diagrams in research papers based on authors' revisions. The system learns from natural language instructions and operates on the editable vector source of figures, allowing users to inspect and edit individual primitives alongside the agent.
What the Document Says
- The paper introduces SciDiagramEdit, a system for automating figure editing in research papers.
- SciDiagramEdit learns from natural language revisions and operates on the editable vector source of figures.
- Users can inspect and co-edit individual primitives with the agent.
Key Concepts Mentioned
- scientific diagram editing
- natural language instructions
- vector source
- skills evolution
Claims Made by the Document
- SciDiagramEdit learns from natural paper revisions.
- SciDiagramEdit operates on the figure's editable vector source.
- Users can inspect and co-edit individual primitives with the agent.
Evidence Used
- Authors describe the learning process of SciDiagramEdit from natural paper revisions.
- The text mentions that SciDiagramEdit operates on the figure's editable vector source.
- Users are mentioned as being able to inspect and co-edit with the agent.
Methods / Approach
UNKNOWN
Limitations Stated by the Authors
UNKNOWN
Limitations Noted by the Agent
Agent interpretation — not from the source.
UNKNOWN
Open Questions
UNKNOWN
Notes for Future Q&A
May include interpretation. Labeled where it does.
UNKNOWN
Raw Abstract / Excerpt
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.
