SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions

• URL: http://arxiv.org/abs/2607.15272v1
• Date: Thu, 16 Jul 2026 17:58:36 GMT
• Title: SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
• Abstract summary: We present SciDiagramEdit, a benchmark and skill-evolution framework that learns from natural paper revisions.<n>An agentic proposer continually refines the agent's skill specification from execution traces over multiple epochs.<n>The resulting skill progressively lifts edit accuracy on a held-out validation set.
• Score: 66.46898035008782
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Papers [2.593510481959727]
  We propose GenGA, a new generation framework that directly produces figures in vector format.<n>By generating figures as a collection of vector elements with a hierarchical structure, GenGA produces outputs that can be seamlessly imported into existing drawing tools.<n> Experimental results show that GenGA achieves superior editing simplicity compared to other methods, and even surpasses human-authored GAs in conciseness and semantic alignment.
  arXiv  Detail & Related papers  (2026-08-05T23:53:02Z)
• SAGE: Structured Agentic Graph Editing for Software Diagrams [5.927477764911397]
  We present SAGE, a browser-based tool for prompt-guided editing of Draw.io and Mermaid-style engineering diagrams.<n>The tool maps diagrams into an editable graph representation, analyzes those intents into graph-oriented operation steps, validates and repairs common Draw.io XML issues, and stores successful results as recoverable versioned artifacts.
  arXiv  Detail & Related papers  (2026-07-01T15:55:09Z)
• WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing [103.68419705566146]
  We present WeEdit, a systematic solution encompassing a scalable data construction pipeline, two benchmarks, and a tailored two-stage training strategy.<n>Specifically, we propose a novel HTML-based automatic editing pipeline, which generates 330K training pairs covering diverse editing operations and 15 languages.<n>On the algorithmic side, we employ glyph-guided supervised fine-tuning to inject explicit spatial and content priors, followed by a multi-objective reinforcement learning stage to align generation with instruction adherence, text clarity, and background preservation.
  arXiv  Detail & Related papers  (2026-03-12T06:25:09Z)
• CoEditor++: Instruction-based Visual Editing via Cognitive Reasoning [98.98349220451216]
  CoEditor++ is a training-free framework that decomposes editing into "what to edit" and "how to edit"<n>We show that CoEditor++ achieves state-of-the-art performance in both general editing and responsible editing tasks.<n>Our findings suggest the potential toward cognitive-centric instruction-based image editing.
  arXiv  Detail & Related papers  (2026-01-31T12:20:46Z)
• Charts Are Not Images: On the Challenges of Scientific Chart Editing [66.38730113476677]
  textitFigEdit is a benchmark for scientific figure editing comprising over 30,000 samples.<n>Our benchmark demonstrates the profound limitations of pixel-level manipulation.<n>By releasing textitFigEdit, we aim to enable systematic progress in structure-aware figure editing.
  arXiv  Detail & Related papers  (2025-11-30T06:13:48Z)
• Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions [20.617718631292696]
  We develop a novel paradigm for instruction-driven image editing that leverages widely available and enormous text-image pairs.<n>Our approach introduces a multi-scale learnable region to localize and guide the editing process.<n>By treating the alignment between images and their textual descriptions as supervision and learning to generate task-specific editing regions, our method achieves high-fidelity, precise, and instruction-consistent image editing.
  arXiv  Detail & Related papers  (2025-05-25T22:40:59Z)
• Improving Iterative Text Revision by Learning Where to Edit from Other Revision Tasks [11.495407637511878]
  Iterative text revision improves text quality by fixing grammatical errors, rephrasing for better readability or contextual appropriateness, or reorganizing sentence structures throughout a document. Most recent research has focused on understanding and classifying different types of edits in the iterative revision process from human-written text. We aim to build an end-to-end text revision system that can iteratively generate helpful edits by explicitly detecting editable spans with their corresponding edit intents.
  arXiv  Detail & Related papers  (2022-12-02T18:10:43Z)
• EditEval: An Instruction-Based Benchmark for Text Improvements [73.5918084416016]
  This work presents EditEval: An instruction-based, benchmark and evaluation suite for automatic evaluation of editing capabilities. We evaluate several pre-trained models, which shows that InstructGPT and PEER perform the best, but that most baselines fall below the supervised SOTA. Our analysis shows that commonly used metrics for editing tasks do not always correlate well, and that optimization for prompts with the highest performance does not necessarily entail the strongest robustness to different models.
  arXiv  Detail & Related papers  (2022-09-27T12:26:05Z)
• Understanding Iterative Revision from Human-Written Text [10.714872525208385]
  IteraTeR is the first large-scale, multi-domain, edit-intention annotated corpus of iteratively revised text. We better understand the text revision process, making vital connections between edit intentions and writing quality.
  arXiv  Detail & Related papers  (2022-03-08T01:47:42Z)
• Learning Structural Edits via Incremental Tree Transformations [102.64394890816178]
  We present a generic model for incremental editing of structured data (i.e., "structural edits") Our editor learns to iteratively generate tree edits (e.g., deleting or adding a subtree) and applies them to the partially edited data. We evaluate our proposed editor on two source code edit datasets, where results show that, with the proposed edit encoder, our editor significantly improves accuracy over previous approaches.
  arXiv  Detail & Related papers  (2021-01-28T16:11:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.