An Empirical Study of VLM Pipelines for Long-Document QA

arXiv:2609.29933 · cs.CL, cs.AI, cs.CV, cs.IR · Submitted 2026-09-24 · Read on arXiv

cs.CL, cs.AI, cs.CV, cs.IR

Submitted: 2026-09-24

Updated: 2026-09-24

Code: https://github.com/QwenLM/Qwen-Agent

Terminology

• Accuracy — 55× in this paper · explained in 1 episode
• Benchmark — 47× in this paper · explained in 2 episodes
• Agentic System — 4× in this paper · explained in 2 episodes
• Thinking mode — 4× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• RAG — 3× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Multi-Agent Framework — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
• MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
• GPT-4o System Card
• FinanceBench: A New Benchmark for Financial Question Answering
• PaperQA: Retrieval-Augmented Generative Agent for Scientific Research
• A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
• LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
• A Comprehensive Survey on Long Context Language Modeling
• Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrieval
• Passage Re-ranking with BERT
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
• DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models
• Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval
• ReAct: Synergizing Reasoning and Acting in Language Models
• DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding

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