# DocR1: Evidence Page-Guided GRPO for Multi-Page Document Understanding

arXiv: https://arxiv.org/abs/2508.07313 · HTML: https://mlsanity.com/paper/2508.07313/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 10 Aug 2025.

## 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, 26 of 26)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [FigureQA: An Annotated Figure Dataset for Visual Reasoning](https://mlsanity.com/paper/1710.07300/) (2017)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document](https://mlsanity.com/paper/2403.04473/) (2024)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding](https://mlsanity.com/paper/2307.02499/) (2023)
- [UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model](https://mlsanity.com/paper/2310.05126/) (2023)
- [MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data](https://mlsanity.com/paper/2206.01347/) (2022)
- [mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding](https://mlsanity.com/paper/2409.03420/) (2024)
- [Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs](https://mlsanity.com/paper/2311.13194/) (2023)
- [MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems](https://mlsanity.com/paper/2410.14179/) (2024)
- [Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks](https://mlsanity.com/paper/2410.01744/) (2024)
- [SpreadsheetLLM: Encoding Spreadsheets for Large Language Models](https://mlsanity.com/paper/2407.09025/) (2024)
- [DOGR: Towards Versatile Visual Document Grounding and Referring](https://mlsanity.com/paper/2411.17125/) (2024)
- [Doc-CoB: Enhancing Document Understanding with Visual Chain-of-Boxes Reasoning](https://mlsanity.com/paper/2505.18603/) (2025)

## Built on by (most cited first, 11 of 11)

- [olmOCR 2: Unit Test Rewards for Document OCR](https://mlsanity.com/paper/2510.19817/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding](https://mlsanity.com/paper/2510.15253/) (2025)
- [VeriCache: Turning Lossy KV Cache into Lossless LLM Inference](https://mlsanity.com/paper/2605.17613/) (2026)
- [CC-OCR V2: Fine-Grained Attribution of LMM Failures in Real-World Visual Document Understanding](https://mlsanity.com/paper/2605.03903/) (2026)
- [Hierarchical Evidence-Driven Reasoning for Long Document Understanding](https://mlsanity.com/paper/2607.04625/) (2026)
- [PriorZero: Bridging Language Priors and World Models for Decision Making](https://mlsanity.com/paper/2605.12289/) (2026)
- [Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels](https://mlsanity.com/paper/2607.24651/) (2026)
- [HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering](https://mlsanity.com/paper/2607.29638/) (2026)
- [DocAtlas: Long-Document Understanding as Mutable-State Interaction](https://mlsanity.com/paper/2608.07527/) (2026)
- [InSight-doc: Agentic Visual Perception for Long-Document Understanding](https://mlsanity.com/paper/2608.10628/) (2026)

## Abstract (arXiv)

Understanding multi-page documents poses a significant challenge for multimodal large language models (MLLMs), as it requires fine-grained visual comprehension and multi-hop reasoning across pages. While prior work has explored reinforcement learning (RL) for enhancing advanced reasoning in MLLMs, its application to multi-page document understanding remains underexplored. In this paper, we introduce DocR1, an MLLM trained with a novel RL framework, Evidence Page-Guided GRPO (EviGRPO). EviGRPO incorporates an evidence-aware reward mechanism that promotes a coarse-to-fine reasoning strategy, guiding the model to first retrieve relevant pages before generating answers. This training paradigm enables us to build high-quality models with limited supervision. To support this, we design a two-stage annotation pipeline and a curriculum learning strategy, based on which we construct two datasets: EviBench, a high-quality training set with 4.8k examples, and ArxivFullQA, an evaluation benchmark with 8.6k QA pairs based on scientific papers. Extensive experiments across a wide range of benchmarks demonstrate that DocR1 achieves state-of-the-art performance on multi-page tasks, while consistently maintaining strong results on single-page benchmarks.