mlsanityData to 14 Oct 2026

DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding

arXiv 2511.11552 ↗First posted 14 Nov 2025cs.CV cs.CLcited by 15

On the map: Multimodal LLMs / vision-language models → Document understanding and multimodal RAG

also in 1 more
Abstract (arXiv)

Comprehending long visual documents, where information is distributed across extensive pages of text and visual elements, is a critical but challenging task for modern Vision-Language Models (VLMs). Existing approaches falter on a fundamental challenge: evidence localization. They struggle to retrieve relevant pages and overlook fine-grained details within visual elements, leading to limited performance and model hallucination. To address this, we propose DocLens, a tool-augmented multi-agent framework that effectively ``zooms in'' on evidence like a lens. 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. Paired with Gemini-2.5-Pro, DocLens achieves state-of-the-art performance on MMLongBench-Doc and FinRAGBench-V, surpassing even human experts. The framework's superiority is particularly evident on vision-centric and unanswerable queries, demonstrating the power of its enhanced localization capabilities.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 36 of its 50 references that are in the map. First posted on arXiv 14 Nov 2025.

Builds on

36 of 50 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing26 Sep
  2. 2025Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling5 Aug
  3. 2024LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating24 Dec
  4. 2024ColPali: Efficient Document Retrieval with Vision Language Models27 Jun

Other references · 32

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  3. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  5. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  6. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 740
  7. 2023YaRN: Efficient Context Window Extension of Large Language Modelscited by 601
  8. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  9. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 433
  10. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  11. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 398
  12. 2025Seed1.5-VL Technical Reportcited by 373
20 more
  1. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 284
  2. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documentscited by 245
  3. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 135
  4. 2023Walking Down the Memory Maze: Beyond Context Limit through Interactive Readingcited by 133
  5. 2025A Comprehensive Survey on Long Context Language Modelingcited by 117
  6. 2025MiMo-VL Technical Reportcited by 115
  7. 2023PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Trainingcited by 111
  8. 2024M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understandingcited by 111
  9. 2023Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documentscited by 104
  10. 2023RecurrentGPT: Interactive Generation of (Arbitrarily) Long Textcited by 84
  11. 2025VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learningcited by 68
  12. 2025MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understandingcited by 67
  13. 2025ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agentscited by 66
  14. 2025MMDocIR: Benchmarking Multimodal Retrieval for Long Documentscited by 43
  15. 2024DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systemscited by 37
  16. 2025Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answeringcited by 36
  17. 2024VISA: Retrieval Augmented Generation with Visual Source Attributioncited by 28
  18. 2025SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinementcited by 28
  19. 2025FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domaincited by 16
  20. 2025A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChatcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 15.

15 papers.

Sort:

By area:

  1. 2026DocDancer: Towards Agentic Document-Grounded Information Seekingcited by 12
  2. 2026Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrievalcited by 8
  3. 2026AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generationcited by 5
  4. 2026CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligencecited by 5
  5. 2026InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social Systemscited by 3
  6. 2026MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QAcited by 2
  7. 2026From Attribution to Abstention: Training-Free Attention-Based Auditing for Clinical Summarizationcited by 1
  8. 2026Exploring Information Seeking Agent Consolidationcited by 0
  9. 2026AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interactioncited by 0
  10. 2026HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answeringcited by 0
  11. 2026DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understandingcited by 0
  12. 2026DocAtlas: Long-Document Understanding as Mutable-State Interactioncited by 0
3 more
  1. 2026Locating Failure in Multi-Page Visually Rich Document Understanding: An Empirical Attributioncited by 0
  2. 2026BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprintscited by 0
  3. 2026It Takes Workflows to Evolve Better Workflowscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding
  2. 2026InSight-doc: Agentic Visual Perception for Long-Document Understanding
  3. 2026Query-Driven Multimodal Information Extraction from Long Documents
  4. 2026Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA
  5. 2026VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents
  6. 2026VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval
  7. 2026VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning
  8. 2026SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding