Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.04390 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914239655968768 |
|---|---|
| author | Huang, Siyuan Gao, Yutong Bai, Juyang Zhou, Yifan Yin, Zi Liu, Xinxin Chellappa, Rama Lau, Chun Pong Nag, Sayan Peng, Cheng Pramanick, Shraman |
| author_facet | Huang, Siyuan Gao, Yutong Bai, Juyang Zhou, Yifan Yin, Zi Liu, Xinxin Chellappa, Rama Lau, Chun Pong Nag, Sayan Peng, Cheng Pramanick, Shraman |
| contents | Creating high-quality figures and visualizations for scientific papers is a time-consuming task that requires both deep domain knowledge and professional design skills. Despite over 2.5 million scientific papers published annually, the figure generation process remains largely manual. We introduce $\textbf{SciFig}$, an end-to-end AI agent system that generates publication-ready pipeline figures directly from research paper texts. SciFig uses a hierarchical layout generation strategy, which parses research descriptions to identify component relationships, groups related elements into functional modules, and generates inter-module connections to establish visual organization. Furthermore, an iterative chain-of-thought (CoT) feedback mechanism progressively improves layouts through multiple rounds of visual analysis and reasoning. We introduce a rubric-based evaluation framework that analyzes 2,219 real scientific figures to extract evaluation rubrics and automatically generates comprehensive evaluation criteria. SciFig demonstrates remarkable performance: achieving 70.1$\%$ overall quality on dataset-level evaluation and 66.2$\%$ on paper-specific evaluation, and consistently high scores across metrics such as visual clarity, structural organization, and scientific accuracy. SciFig figure generation pipeline and our evaluation benchmark will be open-sourced. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04390 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SciFig: Towards Automating Scientific Figure Generation Huang, Siyuan Gao, Yutong Bai, Juyang Zhou, Yifan Yin, Zi Liu, Xinxin Chellappa, Rama Lau, Chun Pong Nag, Sayan Peng, Cheng Pramanick, Shraman Artificial Intelligence Creating high-quality figures and visualizations for scientific papers is a time-consuming task that requires both deep domain knowledge and professional design skills. Despite over 2.5 million scientific papers published annually, the figure generation process remains largely manual. We introduce $\textbf{SciFig}$, an end-to-end AI agent system that generates publication-ready pipeline figures directly from research paper texts. SciFig uses a hierarchical layout generation strategy, which parses research descriptions to identify component relationships, groups related elements into functional modules, and generates inter-module connections to establish visual organization. Furthermore, an iterative chain-of-thought (CoT) feedback mechanism progressively improves layouts through multiple rounds of visual analysis and reasoning. We introduce a rubric-based evaluation framework that analyzes 2,219 real scientific figures to extract evaluation rubrics and automatically generates comprehensive evaluation criteria. SciFig demonstrates remarkable performance: achieving 70.1$\%$ overall quality on dataset-level evaluation and 66.2$\%$ on paper-specific evaluation, and consistently high scores across metrics such as visual clarity, structural organization, and scientific accuracy. SciFig figure generation pipeline and our evaluation benchmark will be open-sourced. |
| title | SciFig: Towards Automating Scientific Figure Generation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.04390 |