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.
| Comments: | 47 pages, 17 figures, 17 tables |
| Subjects: | Artificial Intelligence (cs.AI); Software Engineering (cs.SE) |
| Cite as: | arXiv:2605.10341 [cs.AI] |
| (or arXiv:2605.10341v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.10341 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Cheng Tan [view email]
[v1]
Mon, 11 May 2026 10:43:41 UTC (4,723 KB)