Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA

• URL: http://arxiv.org/abs/2604.13731v1
• Date: Wed, 15 Apr 2026 11:12:27 GMT
• Title: Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA
• Abstract summary: 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.
• Score: 71.42483000929614
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models scale poorly with document length, while visual retrieval-based pipelines are brittle and passive. We propose Doc-$V^*$, an \textbf{OCR-free agentic} framework that casts multi-page DocVQA as sequential evidence aggregation. Doc-$V^*$ begins with a thumbnail overview, then actively navigates via semantic retrieval and targeted page fetching, and aggregates evidence in a structured working memory for grounded reasoning. Trained by imitation learning from expert trajectories and further optimized with Group Relative Policy Optimization, Doc-$V^*$ balances answer accuracy with evidence-seeking efficiency. Across five benchmarks, Doc-$V^*$ outperforms open-source baselines and approaches proprietary models, improving out-of-domain performance by up to \textbf{47.9\%} over RAG baseline. Other results reveal effective evidence aggregation with selective attention, not increased input pages.

Related papers

• DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents [31.706151171213346]
  We introduce DocHop, a benchmark for integrated chart-context reasoning in document-style images.<n>In DocHop, the document narrative specifies multi-step compositional constraints, while charts provide the corresponding data values.<n>We show a substantial gap to human contextnotators achieve over 90% accuracy, while the best model reaches only 62.83%.
  arXiv  Detail & Related papers  (2026-09-02T03:35:12Z)
• DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning [14.841209914774778]
  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.<n>Existing approaches, including end-to-end MLLMs, often lack explicit mechanisms to represent and verify how grounded evidence is progressively composed during reasoning.<n>We propose DocTrace, a hierarchical framework that progressively performs evidence localization, structured document parsing, and evidence graph reasoning.
  arXiv  Detail & Related papers  (2026-08-04T08:04:59Z)
• DocAtlas: Long-Document Understanding as Mutable-State Interaction [67.90400271544678]
  We present DocAtlas, a system that treats long-document understanding as a mutable-state information-seeking process.<n>Given a document and a question, DocAtlas exposes search, reading, note-taking, and review tools, maintains a hierarchical tree and note store, and updates both as the agent records evidence.<n>With GPT-5.4, DocAtlas reaches 71.4% on MMLongBench-Doc, exceeding the human-expert reference of 65.8%.
  arXiv  Detail & Related papers  (2026-07-21T09:45:34Z)
• MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA [14.865891513918278]
  Long-document multimodal question answering requires a system to locate sparse evidence in long PDFs.<n>This paper proposes MAGE-RAG, a multigranular adaptive graph evidence framework for long-document multimodal QA.
  arXiv  Detail & Related papers  (2026-06-14T16:34:15Z)
• Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing [53.41293908252118]
  We introduce Dr. DocBench, a difficulty-aware benchmark for expert-level document parsing.<n>Dr. DocBench spans 52 BISAC domains and selects documents through failure-based sampling.<n>It contains 4,514 annotated pages from long documents averaging around 100 pages, with 65k high-quality annotations for layout, reading order, hierarchical relations, and domain-specific visual contents.<n>Our analysis reveals substantial failures across subjects, content types, and structural attributes, highlighting Dr. DocBench as a comprehensive testbed for diagnosing and advancing document intelligence.
  arXiv  Detail & Related papers  (2026-05-31T18:35:30Z)
• $G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA [53.491241153213565]
  $G2$-Reader is a dual-graph system for multimodal question answering.<n>$G2$-Reader with Qwen3-VL-32B-Instruct reaches 66.21% average accuracy, outperforming strong baselines and a standalone GPT-5 (53.08%)<n>On VisDoMBench across five multimodal domains, $G2$-Reader with Qwen3-VL-32B-Instruct reaches 66.21% average accuracy, outperforming strong baselines and a standalone GPT-5 (53.08%)
  arXiv  Detail & Related papers  (2026-01-29T17:52:54Z)
• Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding [49.26132236798123]
  Vision Language Models (VLMs) have gradually become a primary approach in document understanding.<n>We propose SLEUTH, a multi agent framework that orchestrates a retriever and four collaborative agents in a coarse to fine process.<n>The framework identifies key textual and visual clues within the retrieved pages, filters for salient visual evidence such as tables and charts, and analyzes the query to devise a reasoning strategy.
  arXiv  Detail & Related papers  (2025-11-28T03:09:40Z)
• DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding [59.4112754806335]
  We propose DocLens, a tool-augmented multi-agent framework that effectively zooms in'' on evidence like a lens.<n>It first navigates from the full document to specific visual elements on relevant pages, then employs a sampling-adjudication mechanism to generate a single, reliable answer.<n>It achieves state-of-the-art performance on MMLongBench-Doc and FinRAG-V, surpassing even human experts.
  arXiv  Detail & Related papers  (2025-11-14T18:42:18Z)
• MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval [17.50612953979537]
  MoLoRAG is a logic-aware retrieval framework for multi-modal, multi-page document understanding.<n>It combines semantic and logical relevance to deliver more accurate retrieval.<n>Experiments on four DocQA datasets demonstrate average improvements of 9.68% in accuracy.
  arXiv  Detail & Related papers  (2025-09-06T00:59:28Z)
• Enhancing Document VQA Models via Retrieval-Augmented Generation [1.6769365072542683]
  Document VQA must cope with documents that span dozens of pages, yet leading systems still rely on very large vision-language models.<n>Retrieval-Augmented Generation (RAG) offers an attractive alternative, first retrieving a concise set of relevant segments before generating answers.
  arXiv  Detail & Related papers  (2025-08-26T12:32:55Z)
• SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement [17.272061289197342]
  Document Visual Question Answering (DocVQA) is a practical yet challenging task.<n>Recent methods follow a similar Retrieval Augmented Generation (RAG) pipeline.<n>We introduce SimpleDoc, a lightweight yet powerful retrieval - augmented framework for DocVQA.
  arXiv  Detail & Related papers  (2025-06-16T22:15:58Z)
• M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding [63.33447665725129]
  We introduce M3DocRAG, a novel multi-modal RAG framework that flexibly accommodates various document contexts. M3DocRAG can efficiently handle single or many documents while preserving visual information. We also present M3DocVQA, a new benchmark for evaluating open-domain DocVQA over 3,000+ PDF documents with 40,000+ pages.
  arXiv  Detail & Related papers  (2024-11-07T18:29:38Z)
• End-to-End Multihop Retrieval for Compositional Question Answering over Long Documents [93.55268936974971]
  We propose a multi-hop retrieval method, DocHopper, to answer compositional questions over long documents. At each step, DocHopper retrieves a paragraph or sentence embedding from the document, mixes the retrieved result with the query, and updates the query for the next step. We demonstrate that utilizing document structure in this was can largely improve question-answering and retrieval performance on long documents.
  arXiv  Detail & Related papers  (2021-06-01T03:13:35Z)

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.