HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering

• URL: http://arxiv.org/abs/2607.29638v1
• Date: Fri, 31 Jul 2026 17:17:23 GMT
• Title: HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering
• Abstract summary: Multi-page document visual question answering requires locating sparse evidence at both the page and region levels.<n>We propose HierDoc, a hierarchical evidence-routing framework that formulates long-document evidence acquisition as two-stage set prediction.<n>We show that HierDoc achieves state-of-the-art or competitive performance among open-weight systems.
• Score: 89.21987002412051
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 assume that the relevant pages have already been supplied. Consequently, page and region selection remain disconnected rather than forming successive evidence decisions. We propose HierDoc, a hierarchical evidence-routing framework that formulates long-document evidence acquisition as two-stage set prediction from pages to regions. A page policy selects evidence pages from the full document; these pages are then parsed for semantic elements, after which a region policy selects the elements passed to a downstream answer model. Both answer-agnostic policies are optimized with stage-wise GRPO using granularity-specific structured-set rewards. The answer model receives selected full pages together with selected region crops and OCR or table text, preserving global context while emphasizing fine-grained evidence. Across the evaluated benchmarks, HierDoc achieves state-of-the-art or competitive performance among open-weight systems, improving LongDocURL by 16.87% relative to the strongest reported open-weight baseline. Controlled ablations further show that selected regional evidence improves the page-only system in accuracy and F1 by 5.51% and 4.82%, respectively. These results demonstrate the benefit of organizing coarse page routing and fine-grained region routing as successive, separately optimized stages of a unified evidence-acquisition process.

Related papers

• Hierarchical Evidence-Driven Reasoning for Long Document Understanding [95.51688464037096]
  We introduce HIEVI-RAG, a hierarchical, evidence-driven multimodal RAG framework for closed-domain document understanding.<n>Our framework significantly outperforms existing open-source baselines and exceeds the strongest reported baseline by an average of 8.05% in accuracy.
  arXiv  Detail & Related papers  (2026-07-06T03:08:28Z)
• HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning [17.783618926697066]
  Long-context reasoning requires models to access, retrieve, and integrate evidence scattered across documents, dialogues, and interaction histories.<n>We propose HMARS, a hierarchical multi-agent memory system that treats long contexts as managed memory rather than a flat retrieval corpus.
  arXiv  Detail & Related papers  (2026-06-03T07:15:11Z)
• Structures Facilitate Retrieve, Rerank, and Generate [11.039868951381164]
  Document-grounded dialogue systems (DGDS) utilize knowledge from external documents to answer domain-specific user questions.<n>This paper proposes SF-Re2G to address such issues systematically.
  arXiv  Detail & Related papers  (2026-06-02T07:09:41Z)
• HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering [19.052998569565627]
  HiKEY is a hierarchical tree-based multimodal retrieval framework that elevates document hierarchy to a first-class retrieval signal.<n> Experiments on ODQA benchmarks demonstrate that HiKEY significantly outperforms page- and chunk-based baselines.
  arXiv  Detail & Related papers  (2026-05-28T08:42:21Z)
• DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding [29.270128057512284]
  We introduce DocScope, a benchmark that formulates long-document QA as a structured reasoning trajectory prediction problem.<n>We design a four-stage evaluation protocol that audits each level of the trajectory independently.<n>We benchmark 6 proprietary models, 12 open-weight models, and several domain-specific systems.
  arXiv  Detail & Related papers  (2026-05-09T11:12:59Z)
• Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA [71.42483000929614]
  Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents.<n>We propose Doc-$V*$, an textbfOCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
  arXiv  Detail & Related papers  (2026-04-15T11:12:27Z)
• DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding [63.257540233507626]
  We propose a paradigm that requires the model to execute a structured Analysis, Localization and Reasoning workflow.<n>We show it robustly generalizes from short-page training to ultra-long documents and is naturally synergistic with visual Retrieval-Augmented Generation systems.
  arXiv  Detail & Related papers  (2026-04-14T14:39:26Z)
• MoDora: Tree-Based Semi-Structured Document Analysis System [62.01015188258797]
  Semi-structured documents integrate diverse interleaved data elements arranged in various and often irregular layouts.<n>MoDora is an LLM-powered system for semi-structured document analysis.<n> Experiments show MoDora outperforms baselines by 5.97%-61.07% in accuracy.
  arXiv  Detail & Related papers  (2026-02-26T14:48:49Z)
• RegionRAG: Region-level Retrieval-Augumented Generation for Visually-Rich Documents [40.107303323097646]
  modelname is a novel framework that shifts the retrieval paradigm from the document level to the region level.<n> Experiments on six benchmarks demonstrate that RegionRAG achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-10-31T08:00:32Z)
• RDU: A Region-based Approach to Form-style Document Understanding [69.29541701576858]
  Key Information Extraction (KIE) is aimed at extracting structured information from form-style documents. We develop a new KIE model named Region-based Understanding Document (RDU) RDU takes as input the text content and corresponding coordinates of a document, and tries to predict the result by localizing a bounding-box-like region.
  arXiv  Detail & Related papers  (2022-06-14T14:47:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.