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

arXiv:2604.13731 · cs.CL · Submitted 2026-08-20 · Read on arXiv

Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang Bai

cs.CL

Submitted: 2026-08-20

Updated: 2026-08-21

Terminology

• RAG — 59× in this paper · explained in 3 episodes
• Benchmark — 24× in this paper · explained in 2 episodes
• GRPO — 22× in this paper · explained in 6 episodes
• Accuracy — 16× in this paper · explained in 1 episode
• Aggregation — 15× in this paper · explained in 1 episode
• Robustness — 8× in this paper · explained in 5 episodes
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation — 7× in this paper
• Ablation — 6× in this paper · explained in 1 episode
• Agentic Framework — 6× in this paper · explained in 6 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Group Relative Policy Optimization — 5× in this paper
• Transformer — 5× in this paper · explained in 2 episodes
• Instruction Tuning — 4× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation (RAG) — 4× in this paper · explained in 16 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Active Vision — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Embeddings — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Reward Function — 3× in this paper · explained in 2 episodes
• Supervised Fine-Tuning — 3× in this paper
• Absolute Indices — 2× in this paper · explained in 1 episode
• Action Space — 2× in this paper · explained in 1 episode
• Active Perception — 2× in this paper · explained in 2 episodes
• Adaptive Strategy — 2× in this paper · explained in 1 episode
• Contrastive Learning — 2× in this paper · explained in 5 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Multi-hop Reasoning — 2× in this paper · explained in 3 episodes
• Abstention — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Average Normalized Levenshtein Similarity — 1× in this paper
• Benchmarking — 1× in this paper · explained in 3 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Existing Multi-page Document Visual Question Answering — 1× in this paper
• F1 Score — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Information Gain — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Two-Stage Optimization — 1× in this paper · explained in 2 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Qwen2.5-VL Technical Report
• SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding
• M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding
• Deep Learning based Visually Rich Document Content Understanding: A Survey
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• ColPali: Efficient Document Retrieval with Vision Language Models
• LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• GPT-4o System Card
• TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document
• URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• MinerU: An Open-Source Solution for Precise Document Content Extraction
• VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
• C-Pack: Packed Resources For General Chinese Embeddings
• PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling
• CogDoc: Towards Unified thinking in Documents
• DocAgent: A Multi-Agent System for Automated Code Documentation Generation
• VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering