https://ym-xu.github.io/living-survey/fields/document-understanding/#tag=longdocDocuments beyond a single page: long PDFs, slide decks, collections.Thu, 12 Nov 2026 15:12:01 +0000https://arxiv.org/abs/2610.39308https://arxiv.org/abs/2610.39308Thu, 29 Oct 2026 00:00:00 +0000Shu Wei, Jingjing Wu, Qunyi Xie, Lingshu Zhang, et al. Unlimited OCR ushers the era of long-horizon parsing, substantially mitigating the growth of working memory as document lengthens. However, as document length scales to hundreds of pages, the visual context grows substantially, sharply increasing the computational cost of each decoding step and limiting the scalability…https://arxiv.org/abs/2610.31385https://arxiv.org/abs/2610.31385Thu, 22 Oct 2026 00:00:00 +0000Yufei Tong, Guanjie Cheng, Tianle Wu, Leilei Zhang, et al. Visual document understanding is essential for acquiring knowledge from visually rich documents and is attracting growing research interest. Existing surveys emphasize architectures or technical approaches, with limited attention to how task bottlenecks shape technical choices and research priorities. We present a task…https://arxiv.org/abs/2610.28957https://arxiv.org/abs/2610.28957Tue, 20 Oct 2026 00:00:00 +0000Juan Terven, Diana-Margarita Córdova-Esparza, Julio-Alejandro Romero-González, Edgar Chavez-Urbiola, et al. Scanning every passage in a long document seems thorough, but does it preserve more useful evidence or produce better answers? We compare 11 retrieval configurations spanning lexical and dense search, hybrid reranking, and full-document scanning with Jev, OpenAI Decisions, and Cloudflare Clef. Our evaluation uses 396 Q…https://arxiv.org/abs/2610.21327https://arxiv.org/abs/2610.21327Thu, 15 Oct 2026 00:00:00 +0000Zhuowen Liang, Xiaotian Lin, Yuyu Luo, Haixun Wang, et al. Multimodal long-document question answering requires models to seek sparse evidence across pages and modalities, understand heterogeneous document content, and reason over the collected evidence. Even advanced vision-language models (VLMs) can overlook sparse evidence and struggle with cross-modal reasoning in a single…https://arxiv.org/abs/2610.20964https://arxiv.org/abs/2610.20964Wed, 14 Oct 2026 00:00:00 +0000Zhivar Sourati, Marianne Menglin Liu, Rongguang Wang, Zheng Wang, et al. Existing long-document QA benchmarks rarely combine large-scale human-authored questions with detailed visual evidence annotations, limiting diagnosis of evidence localization and interpretation failures. We present VELD-QA, a large-scale benchmark for Visual Evidence grounding and question answering in Long Documents.…https://arxiv.org/abs/2610.18238https://arxiv.org/abs/2610.18238Tue, 13 Oct 2026 00:00:00 +0000Qian Chen, Xianyin Zhang, Lifan Guo, Chi Zhang Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page-level elements. However, downstream applications such as retrieval-augmented generation (RAG) also require coherent document-level structure. Although these models ind…https://arxiv.org/abs/2610.17057https://arxiv.org/abs/2610.17057Mon, 12 Oct 2026 00:00:00 +0000Simon Ott, Yufan Chen, Ruiping Liu, Junwei Zheng, et al. · NeurIPS 2026 Vision-based document retrieval has improved rapidly, but current evaluation settings still emphasize short documents and single relevant pages. This leaves an important gap between leaderboard performance and realistic long-document retrieval, where the evidence needed to answer a query may span multiple pages or even…https://arxiv.org/abs/2609.29933https://arxiv.org/abs/2609.29933Thu, 24 Sep 2026 00:00:00 +0000Kenan E. Ak, Jay Mohta, Gwang Gook Lee, Yan Xu, et al. Vision-Language Models (VLMs) are increasingly used for long-document processing, where the inputs combine text with charts, tables, figures, and complex layouts. Deploying them means choosing how to feed the document to the model, which retriever to use when only a subset of pages is sent, and whether to run the model…https://arxiv.org/abs/2609.13268https://arxiv.org/abs/2609.13268Mon, 07 Sep 2026 00:00:00 +0000Amirul Rahman, Aisha Karim, Kenji Nakamura, Yi-Fan Ng Annual reports, diligence packs, and infographic dashboards bury numbers in page images: axes, cell grids, and footnotes that OCR pipelines flatten and that page-level visual retrievers still treat as interchangeable in-context examples. We keep a frozen Qwen2.5-VL-7B-Instruct generator and a ColPali / VisRAG-Ret page …https://arxiv.org/abs/2609.05802https://arxiv.org/abs/2609.05802Sat, 05 Sep 2026 00:00:00 +0000Chen Qian, Yimeng Wang, Yu Chen, Lingfei Wu, et al. Large language models answering questions over multi-page documents are expected to cite the supporting pages, yet supplied citations are sometimes inaccurate, and current evaluations score citations at generation time or against text passages: no existing benchmark evaluates whether a system can verify and correct a p…https://arxiv.org/abs/2608.25618https://arxiv.org/abs/2608.25618Wed, 26 Aug 2026 00:00:00 +0000Dongzhuoran Zhou, Yuqicheng Zhu, Yule Liu, Zhen Yang, et al. · EMNLP 2026 Findings Long-document visual question answering increasingly relies on VLM agents that retrieve candidate pages, inspect page images, write findings to working memory, and synthesize answers. Working memory should carry answer-supporting evidence across page inspections for later grounded answering, yet existing evaluation mai…https://arxiv.org/abs/2608.22214https://arxiv.org/abs/2608.22214Sun, 23 Aug 2026 00:00:00 +0000Yikai Gao, Ding Xia, Xi Yang In domain-specific multimodal long documents, images and text jointly convey complex knowledge that cannot be fully captured by plain text alone. However, existing paradigms like DocVQA primarily focus on generating textual answers or localizing evidence regions, rather than outputting query-specific textual attribute …https://arxiv.org/abs/2608.16417https://arxiv.org/abs/2608.16417Mon, 17 Aug 2026 00:00:00 +0000Hao Zhang, Longrong Yang, Lunhao Duan, Ziyang Wang, et al. Multi-modal retrieval-augmented generation (RAG) is a key technique for visually rich long document understanding. Existing multi-modal RAG methods are progressively advancing toward multi-agent systems: they first retrieve relevant pages based on a query, and then iteratively understand information within those pages.…https://arxiv.org/abs/2608.15064https://arxiv.org/abs/2608.15064Sat, 15 Aug 2026 00:00:00 +0000Yuefeng Zou, Yichen Lu, Jingxiao Yang, Bingtao Fu, et al. Parsing visual documents into machine-readable representations is fundamental to document intelligence. Existing benchmarks focus on page-level element recognition, reading order, formula recognition, and table structure. Long documents, however, also require document-level structure recovery. This includes reconstruct…https://arxiv.org/abs/2608.14841https://arxiv.org/abs/2608.14841Fri, 14 Aug 2026 00:00:00 +0000Guanchen Wu, Jiayuan Ding, Subhabrata Mukherjee, Carl Yang Long-document visual question answering (VQA) over documents of tens to hundreds of pages mixing text, tables, charts, and figures typically follows retrieve-then-read pipelines. In our setting, the bottleneck shifts from retrieval recall to reranker-side evidence selection: on MMLongBench-Doc, BGE-M3 reaches Recall@20…https://arxiv.org/abs/2608.14055https://arxiv.org/abs/2608.14055Fri, 14 Aug 2026 00:00:00 +0000Ziqi Song, Zongyuan Xiang, James G. Ogg, Bruce S. Lieberman, et al. Authoritative scientific knowledge in geoscience remains largely trapped in legacy monographs and historical literature, where unstructured text and complex layouts hinder computational access. We introduce HERMES, a scalable multi-agent framework that extracts structured data from ultra-long scientific documents. Usin…https://arxiv.org/abs/2608.10628https://arxiv.org/abs/2608.10628Tue, 11 Aug 2026 00:00:00 +0000Kaican Li, Weiyan Xie, Lewei Yao, Jiannan Wu, et al. · EMNLP 2026 Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot. In this work, we propose InSight-doc, an agentic visual perception framework that treats visual resolution as an adaptive reasoning-time resource. InSight-doc starts from low resolution …https://arxiv.org/abs/2608.07943https://arxiv.org/abs/2608.07943Sat, 08 Aug 2026 00:00:00 +0000Lewei Xu, Yihao Ding, Zihan Xu, Daniel Yitian Su, et al. Multi-page visually rich document understanding (MP-VRDU) systems can fail when evidence is not faithfully represented, not selected, or not used correctly, yet final accuracy alone does not reveal where failures occur. We present an empirical attribution framework that examines these failures through controlled interv…https://arxiv.org/abs/2608.07067https://arxiv.org/abs/2608.07067Fri, 07 Aug 2026 00:00:00 +0000Hanshu Yao, Janfeng Zhong, Niu Lian, Jinpeng Wang Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static retrieval and fragile cross-round memory. Mainstream single-round methods commit to a fixed top-$k$ page set at the outset and struggle to recover from early retrieval …https://arxiv.org/abs/2608.03292https://arxiv.org/abs/2608.03292Tue, 04 Aug 2026 00:00:00 +0000Le Xiang, Zhicheng Guan, Hong Chen, Xiaocong Lin, et al. Long Document Visual Question Answering (LongDocVQA) requires Multimodal Large Language Models (MLLMs) to locate, integrate, and reason over heterogeneous document elements distributed across multiple pages. Existing approaches, including end-to-end MLLMs, retrieval-augmented generation (RAG) pipelines, and document ag…https://arxiv.org/abs/2607.29638https://arxiv.org/abs/2607.29638Fri, 31 Jul 2026 00:00:00 +0000Rongjian Gu, Wengang Zhou, Junyu Xiong, Yonghui Wang, et al. Multi-page document visual question answering requires locating sparse evidence at both the page and region levels. Existing approaches typically emphasize one level over the other: page-centric methods focus on page acquisition, with region operations serving mainly as navigation aids, whereas region-centric methods a…https://arxiv.org/abs/2608.07527https://arxiv.org/abs/2608.07527Tue, 21 Jul 2026 00:00:00 +0000Hongchen Wei, Yuanzhe Wang, Bei Liu, Yifan Yang, et al. Long-document understanding requires models to find and combine evidence across many pages, layouts, tables, figures, and charts. Existing retrieval-augmented systems usually select evidence from a static index before generation, while recent agentic systems add multi-turn tool use but often rely on frozen proprietary …https://arxiv.org/abs/2608.00036https://arxiv.org/abs/2608.00036Tue, 21 Jul 2026 00:00:00 +0000Hongchen Wei, Yuanzhe Wang, Bei Liu, Yifan Yang, et al. Real-world document tasks often ask professionals to answer questions from annual reports, regulations, clinical guidelines, and technical manuals that span hundreds or thousands of pages. Some questions also require comparing related reports. Reliable long-document understanding is therefore a prerequisite for using L…https://arxiv.org/abs/2607.18917https://arxiv.org/abs/2607.18917Tue, 21 Jul 2026 00:00:00 +0000Zhong Ji, Keqi Jin, Yan Zhang, Jiasheng Li · EMNLP 2026 Long-document multimodal question answering requires more than retrieving relevant chunks from a large document. Different queries require different evidence behavior. Existing multimodal RAG systems improve evidence access through text chunks, page images, graph links, or heterogeneous document elements, but they ofte…https://arxiv.org/abs/2607.22679https://arxiv.org/abs/2607.22679Sat, 11 Jul 2026 00:00:00 +0000Bohou Li, Benjamin Sowell, Mehul Shah, Mark Lindblad, et al. In visually-rich documents, information is encoded not only in individual page objects such as tables, headers, and text blocks, but also in the structural relations among them, making document structure analysis fundamental to information retrieval and document understanding. However, accurately inferring such relatio…https://arxiv.org/abs/2607.10400https://arxiv.org/abs/2607.10400Sat, 11 Jul 2026 00:00:00 +0000Abhigya Verma, Khyati Mahajan, Amit Kumar Saha, Shruthan Radhakrishna, et al. Vision language models (VLMs) have achieved strong performance on visual document understanding benchmarks such as DocVQA, ChartQA, and MMLongBench-Doc. However, real-world documents combine multiple factors such as length, layout complexity, modality, and question difficulty, which makes it difficult to attribute mode…https://arxiv.org/abs/2607.04625https://arxiv.org/abs/2607.04625Mon, 06 Jul 2026 00:00:00 +0000Junyu Xiong, Yonghui Wang, Rongjian Gu, Chenyu Liu, et al. Retrieval-Augmented Generation (RAG) streamlines long-document understanding by leveraging retrieval mechanisms to restrict input images to a highly curated subset. However, existing multimodal RAG pipelines primarily face two critical challenges: first, standard semantic similarity retrievers frequently fetch topicall…https://arxiv.org/abs/2607.01420https://arxiv.org/abs/2607.01420Wed, 01 Jul 2026 00:00:00 +0000Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi, Sai Soorya Rao Veeravalli, et al. As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and model safety. While unimodal attributions have been explored in depth, the multimodal setting remains relatively under-researched. As a result, we introduce MultAttnAttr…https://arxiv.org/abs/2606.25491https://arxiv.org/abs/2606.25491Wed, 24 Jun 2026 00:00:00 +0000Chuangxin Zhao, Boyan Shi, Yanling Wang, Yijian LU, et al. Automated homework assessment depends not only on recognizing student answers, but also on accurately locating where each answer and each intermediate reasoning step appears in noisy, multi-page handwritten work. This paper addresses the missing evaluation setting of page-aware, two-level answer-region grounding: given…https://arxiv.org/abs/2606.15906https://arxiv.org/abs/2606.15906Sun, 14 Jun 2026 00:00:00 +0000Yilong Zuo, Xunkai Li, Jing Yuan, Qiangqiang Dai, et al. Long-document multimodal question answering requires a system to locate sparse evidence in long PDFs and integrate clues from text, tables, images, charts, and complex layouts. Existing RAG methods mostly rely on fixed Top-k retrieval over text chunks or pages. Text retrieval can compress the context but often loses vi…https://arxiv.org/abs/2606.12898https://arxiv.org/abs/2606.12898Thu, 11 Jun 2026 00:00:00 +0000Shenglai Zeng, Qirui Wang, Kai Guo, Xinnan Dai, et al. Visual Text Comprehension (VTC) renders text into images for a vision-language model (VLM) to read, sidestepping LLM context-window limits and powering applications from long-page OCR to multi-page memory QA. Yet existing VTC pipelines treat rendering and layout as a fixed, content-agnostic preprocessing step and offer…https://arxiv.org/abs/2607.24748https://arxiv.org/abs/2607.24748Thu, 21 May 2026 00:00:00 +0000Seonok Kim Visually-rich documents such as reports, slides, and manuals often distribute the evidence needed to answer a question across multiple pages, mixing text with layout cues, tables, charts, and figures. This work studies multimodal retrieval-augmented generation for question answering over such visually-rich long documen…https://arxiv.org/abs/2605.22100https://arxiv.org/abs/2605.22100Thu, 21 May 2026 00:00:00 +0000Bangbang Zhou, Hangdi Xing, Yifan Chen, Jianjun Xu, et al. Document parsing converts visually rich documents into machine-readable structured representations, forming a crucial foundation for information systems. Although many benchmarks have been proposed for document parsing, they remain inadequate for realistic scenarios. Existing benchmarks either focus on specific tasks o…https://arxiv.org/abs/2605.17356https://arxiv.org/abs/2605.17356Sun, 17 May 2026 00:00:00 +0000Bo Zhao, Maosheng Pang, Chen Zhang, Huan Yang, et al. Existing works typically focus on presentation generation under isolated input settings, whereas real-world use cases span diverse scenarios, including vague user prompts, long documents, multimodal materials, and multiple heterogeneous sources. Moreover, current evaluations are often insufficiently scenario-specific. …