The paper introduces page‑centric Visual Document Retrieval (VDR), treating pages as the primary indexing units while leveraging document context for relevance assessment. It distinguishes page and document retrieval granularities and three retrieval paradigms—independent‑item, evidence‑set, and iterative—then evaluates 42 existing benchmarks across eight criteria. The analysis reveals that most current VDR research focuses on page‑level independent‑item retrieval, with limited support for document‑level, evidence‑set, and iterative settings, and that realistic user queries and graded relevance judgments are rarely used, highlighting gaps between application needs and evaluation protocols.
arXiv:2610.17057v1 Announce Type: new Abstract: Vision-based document retrieval has improved rapidly, but current evaluation settings still emphasize short documents and single relevant pages. This l...
VisDocAgentBench is a closed‑corpus benchmark that evaluates static versus agentic retrieval for visually rich documents, using 2,375 pages from 100 documents and 120 queries that span direct, one‑bridge, and two‑bridge evidence structures. The benchmark includes semantic, relational, and visual queries, full‑document review, and hard‑negative validation. Results show that a strong visual retriever performs well on direct items but poorly on two‑bridge items, while agents improve performance, especially when using visual retrieval and iterative search capabilities.
arXiv:2610.20367v1 Announce Type: new Abstract: Retrieving information from visually rich documents requires matching queries against pages that contain complex evidence in tables, figures, and layou...
arXiv:2607. 24748v1 Announce Type: cross Abstract: 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.
arXiv:2608. 14841v1 Announce Type: new Abstract: 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.
arXiv:2609.07262v1 Announce Type: cross Abstract: Late-interaction visual document retrievers preserve fine-grained page evidence by storing many token embeddings per page, but the resulting storage...
The paper introduces Invoice Haystack, a benchmark of 1,500 anonymized invoices and 200 question‑answer pairs that tests document retrieval and visual question answering under strong visual homogeneity. It shows that existing benchmarks suffer from embedding collapse, with Invoice Haystack’s mean pairwise cosine similarity at 0.73 versus 0.38 and 0.31 in DocHaystack and InfoHaystack. The authors propose VL‑RAG, a hybrid retrieval‑augmented generation framework that combines text and visual embeddings and a VLM‑based verification filter, achieving 60.0% Recall@1 on Invoice Haystack‑500 and improving performance on other benchmarks.
arXiv:2608. 15064v1 Announce Type: new Abstract: Parsing visual documents into machine-readable representations is fundamental to document intelligence.
The paper surveys long-document visual question answering (VQA) from a task-centric perspective, breaking it down into document parsing, evidence organization and retrieval, generator organization and learning, and evaluation. It introduces a detailed taxonomy for each component, tracks how research priorities have shifted over time—from multimodal content understanding to evidence acquisition and management—and highlights the importance of explicit retrieval alongside direct reading. The authors propose future research directions focused on evidence sufficiency, verifiable and correctable understanding, budget-aware coordination, and continual document understanding.
arXiv:2607. 24781v1 Announce Type: cross Abstract: RAG systems rely on chunking, which destroys structural information in documents.
arXiv:2608.21714v1 Announce Type: new Abstract: Recent page-image retrievers such as ColPali have improved retrieval over visually rich documents, yet little is known about how they behave in cross-l...
arXiv:2608. 07067v1 Announce Type: new Abstract: 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.