| title | PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents |
|---|---|
| authors | Bihui Yu, Xinglong Xu, Junjie Jiang, Jiabei Cheng, Caijun Jia, Siyuan Li, Conghui He, Jingxuan Wei, Cheng Tan |
| date | 2026-05-11 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.10341 |
| affiliation | OpenDataLab |
| upvotes | 32 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | A LaTeX manuscript that compiles without error is not necessarily publication-ready. The resulting PDFs frequently suffer from misplaced floats, overflowing equations, inconsistent table scaling, widow and orphan lines, and poor page balance, forcing authors into repetitive compile-inspect-edit cycles. Rule-based tools are blind to rendered visuals, operating only on source code and log files. Text-only LLMs perform open-loop text editing, unable to predict or verify the two-dimensional layout consequences of their changes. Reliable typesetting optimization therefore requires a visual closed loop with verification after every edit. We formalize this problem as Visual Typesetting Optimization (VTO), the task of transforming a compilable LaTeX paper into a visually polished, page-budget-compliant PDF through iterative visual verification and source-level revision, and introduce a five-category taxonomy of typesetting defects to guide diagnosis. We present PaperFit, a vision-in-the-loop agent that iteratively renders pages, diagnoses defects, and applies constrained repairs. To benchmark VTO, we construct PaperFit-Bench with 200 papers across 10 venue templates and 13 defect types at different difficulty. Extensive experiments show that PaperFit outperforms all baselines by a large margin, establishing that bridging the gap from compilable source to publication-ready PDF requires vision-in-the-loop optimization and that VTO constitutes a critical missing stage in the document automation pipeline. |
cite
@misc{yu2026paperfit,
title={PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents},
author={Bihui Yu and Xinglong Xu and Junjie Jiang and Jiabei Cheng and Caijun Jia and Siyuan Li and Conghui He and Jingxuan Wei and Cheng Tan},
year={2026},
eprint={2605.10341},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.10341}
}