Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.10341 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917480035778560 |
|---|---|
| author | Yu, Bihui Xu, Xinglong Jiang, Junjie Cheng, Jiabei Jia, Caijun Li, Siyuan He, Conghui Wei, Jingxuan Tan, Cheng |
| author_facet | Yu, Bihui Xu, Xinglong Jiang, Junjie Cheng, Jiabei Jia, Caijun Li, Siyuan He, Conghui Wei, Jingxuan Tan, Cheng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10341 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents Yu, Bihui Xu, Xinglong Jiang, Junjie Cheng, Jiabei Jia, Caijun Li, Siyuan He, Conghui Wei, Jingxuan Tan, Cheng Artificial Intelligence Software Engineering 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. |
| title | PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents |
| topic | Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2605.10341 |