Preprint · 2026 · Open access

AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations

Minjun Zhu, Zhen Lin, Yixuan Weng, Panzhong Lu, Qiujie Xie, Yifan Wei, Sifan Liu, Qiyao Sun, Yue Zhang

arXiv (Cornell University) · Published 3 February 2026 · DOI 10.48550/arxiv.2602.03828

Free PDFView at the publisherCite this paper

In brief

“AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations” is a 2026 preprint by Minjun Zhu and 8 co-authors, published in arXiv (Cornell University). OpenAlex counts 19 citations as of 15 November 2026. It is open access under a CC BY-NC-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
19
Most cited in
2026 (19)
References
19
Authors
9

Abstract

High-quality scientific illustrations are crucial for effectively communicating complex scientific and technical concepts, yet their manual creation remains a well-recognized bottleneck in both academia and industry. We present FigureBench, the first large-scale benchmark for generating scientific illustrations from long-form scientific texts. It contains 3,300 high-quality scientific text-figure pairs, covering diverse text-to-illustration tasks from scientific papers, surveys, blogs, and textbooks. Moreover, we propose AutoFigure, the first agentic framework that automatically generates high-quality scientific illustrations based on long-form scientific text. Specifically, before rendering the final result, AutoFigure engages in extensive thinking, recombination, and validation to produce a layout that is both structurally sound and aesthetically refined, outputting a scientific illustration that achieves both structural completeness and aesthetic appeal. Leveraging the high-quality data from FigureBench, we conduct extensive experiments to test the performance of AutoFigure against various baseline methods. The results demonstrate that AutoFigure consistently surpasses all baseline methods, producing publication-ready scientific illustrations. The code, dataset and huggingface space are released in https://github.com/ResearAI/AutoFigure.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Zhu, M., Lin, Z., Weng, Y., Lu, P., Xie, Q., Wei, Y., Liu, S., Sun, Q., & Zhang, Y. (2026). AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.03828

MLA 9

Zhu, Minjun, et al. “AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2602.03828.

Chicago

Zhu, Minjun, Zhen Lin, Yixuan Weng, Panzhong Lu, Qiujie Xie, Yifan Wei, Sifan Liu, Qiyao Sun, and Yue Zhang. 2026. “AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.03828.

Harvard

Zhu, M. et al. (2026) ‘AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations’, arXiv (Cornell University). doi:10.48550/arxiv.2602.03828.

IEEE

M. Zhu et al., “AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2602.03828.

BibTeX

@misc{zhu2026autofigure,
  title     = {{AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations}},
  author    = {Zhu, Minjun and Lin, Zhen and Weng, Yixuan and Lu, Panzhong and Xie, Qiujie and Wei, Yifan and Liu, Sifan and Sun, Qiyao and Zhang, Yue},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2602.03828},
  url       = {https://doi.org/10.48550/arxiv.2602.03828}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis

  • large-scale benchmark
  • agentic framework
  • publication-ready figures

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Zhu, M., Lin, Z., Weng, Y., Lu, P., Xie, Q., Wei, Y., Liu, S., Sun, Q., & Zhang, Y. (2026). AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.03828

How many times has this paper been cited?

19 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Minjun Zhu, Zhen Lin, Yixuan Weng, Panzhong Lu, Qiujie Xie, Yifan Wei, Sifan Liu, Qiyao Sun, Yue Zhang.

What is the DOI of this paper?

10.48550/arxiv.2602.03828. The permanent link is https://doi.org/10.48550/arxiv.2602.03828.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.