Rethinking RAG in Long Videos: What to Retrieve and How to Use It?

arXiv:2606.13141 · cs.AI · Submitted 2026-06-11 · Read on arXiv

cs.AI

Submitted: 2026-06-11

Updated: 2026-10-02

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 2× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes

Sources

• Qwen3-VL Technical Report
• Moment Sampling in Video LLMs for Long-Form Video QA
• CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
• Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline
• ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
• VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
• PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks
• Semantic Event Graphs for Long-Form Video Question Answering
• CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content
• DAT: Dynamic Alpha Tuning for Hybrid Retrieval in Retrieval-Augmented Generation
• VideoChat: Chat-Centric Video Understanding
• Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
• Video-Oasis: Rethinking Evaluation of Video Understanding
• MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs
• Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval
• Advancing Egocentric Video Question Answering with Multimodal Large Language Models
• RAG-Fusion: a New Take on Retrieval-Augmented Generation
• Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
• EVA-CLIP: Improved Training Techniques for CLIP at Scale
• EgoGraph: Temporal Knowledge Graph for Egocentric Video Understanding

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems