# LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating

arXiv: https://arxiv.org/abs/2412.18424 · HTML: https://mlsanity.com/paper/2412.18424/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 24 of 24)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [DocFormer: End-to-End Transformer for Document Understanding](https://mlsanity.com/paper/2106.11539/) (2021)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [MANTIS: Interleaved Multi-Image Instruction Tuning](https://mlsanity.com/paper/2405.01483/) (2024)
- [MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations](https://mlsanity.com/paper/2407.01523/) (2024)
- [TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document](https://mlsanity.com/paper/2403.04473/) (2024)
- [InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD](https://mlsanity.com/paper/2404.06512/) (2024)
- [Document Understanding Dataset and Evaluation (DUDE)](https://mlsanity.com/paper/2305.08455/) (2023)
- [mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding](https://mlsanity.com/paper/2409.03420/) (2024)
- [M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding](https://mlsanity.com/paper/2411.04952/) (2024)
- [Hierarchical multimodal transformers for Multi-Page DocVQA](https://mlsanity.com/paper/2212.05935/) (2022)
- [M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework](https://mlsanity.com/paper/2411.06176/) (2024)
- [GRAM: Global Reasoning for Multi-Page VQA](https://mlsanity.com/paper/2401.03411/) (2024)
- [Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks](https://mlsanity.com/paper/2410.01744/) (2024)
- [WebQuest: A Benchmark for Multimodal QA on Web Page Sequences](https://mlsanity.com/paper/2409.13711/) (2024)
- [Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism](https://mlsanity.com/paper/2404.19024/) (2024)

## Built on by (most cited first, 30 of 72)

- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding](https://mlsanity.com/paper/2503.13964/) (2025)
- [Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs](https://mlsanity.com/paper/2507.09477/) (2025)
- [MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly](https://mlsanity.com/paper/2505.10610/) (2025)
- [SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement](https://mlsanity.com/paper/2506.14035/) (2025)
- [Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding](https://mlsanity.com/paper/2511.22850/) (2025)
- [MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval](https://mlsanity.com/paper/2509.07666/) (2025)
- [DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding](https://mlsanity.com/paper/2511.11552/) (2025)
- [a1: Steep Test-time Scaling Law via Environment Augmented Generation](https://mlsanity.com/paper/2504.14597/) (2025)
- [DocDancer: Towards Agentic Document-Grounded Information Seeking](https://mlsanity.com/paper/2601.05163/) (2026)
- [Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding](https://mlsanity.com/paper/2510.15253/) (2025)
- [Structured Attention Matters to Multimodal LLMs in Document Understanding](https://mlsanity.com/paper/2506.21600/) (2025)
- [A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends](https://mlsanity.com/paper/2507.09861/) (2025)
- [RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding](https://mlsanity.com/paper/2510.27261/) (2025)
- [LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding](https://mlsanity.com/paper/2510.07233/) (2025)
- [MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models](https://mlsanity.com/paper/2605.14906/) (2026)
- [Large Language Models as Computable Approximations to Solomonoff Induction](https://mlsanity.com/paper/2505.15784/) (2025)
- [Do LLMs Truly Understand When a Precedent Is Overruled?](https://mlsanity.com/paper/2510.20941/) (2025)
- [AEC-Bench: A Multimodal Benchmark for Agentic Systems in Architecture, Engineering, and Construction](https://mlsanity.com/paper/2603.29199/) (2026)
- [URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding](https://mlsanity.com/paper/2511.10552/) (2025)
- [MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning](https://mlsanity.com/paper/2604.13579/) (2026)
- [CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence](https://mlsanity.com/paper/2605.12882/) (2026)
- [MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks](https://mlsanity.com/paper/2507.18932/) (2025)
- [Multi-Agent Interactive Question Generation Framework for Long Document Understanding](https://mlsanity.com/paper/2507.20145/) (2025)
- [Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy](https://mlsanity.com/paper/2510.22215/) (2025)
- [RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension](https://mlsanity.com/paper/2601.14289/) (2026)
- [MLDocRAG: Multimodal Long-Context Document Retrieval Augmented Generation](https://mlsanity.com/paper/2602.10271/) (2026)
- [M3DR: Towards Universal Multilingual Multimodal Document Retrieval](https://mlsanity.com/paper/2512.03514/) (2025)
- [SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature](https://mlsanity.com/paper/2601.10108/) (2026)
- [ALDEN: Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents](https://mlsanity.com/paper/2510.25668/) (2025)

## Abstract (arXiv)

Large vision language models (LVLMs) have improved the document understanding capabilities remarkably, enabling the handling of complex document elements, longer contexts, and a wider range of tasks. However, existing document understanding benchmarks have been limited to handling only a small number of pages and fail to provide a comprehensive analysis of layout elements locating. In this paper, we first define three primary task categories: Long Document Understanding, numerical Reasoning, and cross-element Locating, and then propose a comprehensive benchmark, LongDocURL, integrating above three primary tasks and comprising 20 sub-tasks categorized based on different primary tasks and answer evidences. Furthermore, we develop a semi-automated construction pipeline and collect 2,325 high-quality question-answering pairs, covering more than 33,000 pages of documents, significantly outperforming existing benchmarks. Subsequently, we conduct comprehensive evaluation experiments on both open-source and closed-source models across 26 different configurations, revealing critical performance gaps in this field.