Agentar-Fin-OCR
2026-03-11 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed Agentar-Fin-OCR, a system designed to convert very long financial PDFs into accurate and structured digital formats. Their method includes new techniques to handle tricky financial layouts and reconstruct document structure across multiple pages. They also created a new benchmark called FinDocBench, which tests models on various financial document types with expert-verified annotations. Their experiments show that Agentar-Fin-OCR performs well compared to other models, making it a useful tool for handling financial documents reliably.
financial documentsPDF parsingtable parsingdocument structurecross-page consolidationcurriculum learningbenchmark datasetTable of Contentsedit-distanceIntersection over Union
Authors
Siyi Qian, Xiongfei Bai, Bingtao Fu, Yichen Lu, Gaoyang Zhang, Xudong Yang, Peng Zhang
Abstract
In this paper, we propose Agentar-Fin-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semantically consistent, highly accurate, structured outputs with auditing-grade provenance. To address finance-specific challenges such as complex layouts, cross-page structural discontinuities, and cell-level referencing capability, Agentar-Fin-OCR combines (1) a Cross-page Contents Consolidation algorithm to restore continuity across pages and a Document-level Heading Hierarchy Reconstruction (DHR) module to build a globally consistent Table of Contents (TOC) tree for structure-aware retrieval, and (2) a difficulty-adaptive curriculum learning training strategy for table parsing, together with a CellBBoxRegressor module that uses structural anchor tokens to localize table cells from decoder hidden states without external detectors. Experiments demonstrate that our model shows high performance on the table parsing metrics of OmniDocBench. To enable realistic evaluation in the financial vertical, we further introduce FinDocBench, a benchmark that includes six financial document categories with expert-verified annotations and evaluation metrics including Table of Contents edit-distance-based similarity (TocEDS), cross-page concatenated TEDS, and Table Cell Intersection over Union (C-IoU). We evaluate a wide range of state-of-the-art models on FinDocBench to assess their capabilities and remaining limitations on financial documents. Overall, Agentar-Fin-OCR and FinDocBench provide a practical foundation for reliable downstream financial document applications.