mlsanityData to 7 Oct 2026

VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos

arXiv 2502.01549 ↗First posted 3 Feb 2025cs.IR cs.AI cs.CVcited by 76

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has demonstrated remarkable success in enhancing Large Language Models (LLMs) through external knowledge integration, yet its application has primarily focused on textual content, leaving the rich domain of multi-modal video knowledge predominantly unexplored. This paper introduces VideoRAG, the first retrieval-augmented generation framework specifically designed for processing and understanding extremely long-context videos. Our core innovation lies in its dual-channel architecture that seamlessly integrates (i) graph-based textual knowledge grounding for capturing cross-video semantic relationships, and (ii) multi-modal context encoding for efficiently preserving visual features. This novel design empowers VideoRAG to process unlimited-length videos by constructing precise knowledge graphs that span multiple videos while maintaining semantic dependencies through specialized multi-modal retrieval paradigms. Through comprehensive empirical evaluation on our proposed LongerVideos benchmark-comprising over 160 videos totaling 134+ hours across lecture, documentary, and entertainment categories-VideoRAG demonstrates substantial performance compared to existing RAG alternatives and long video understanding methods. The source code of VideoRAG implementation and the benchmark dataset are openly available at: https://github.com/HKUDS/VideoRAG.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 31 of its 38 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

31 of 38 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension20 Nov
  2. 2024ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems25 Oct
  3. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents14 Oct
  4. 2024iRAG: Advancing RAG for Videos with an Incremental Approach18 Apr

Other references · 27

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  4. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  6. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,375
  7. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  8. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,061
  9. 2023EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understandingcited by 666
  10. 2024LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understandingcited by 644
  11. 2023LLaMA-VID: An Image is Worth 2 Tokens in Large Language Modelscited by 539
  12. 2024Long Context Transfer from Language to Visioncited by 502
15 more
  1. 2025VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understandingcited by 502
  2. 2024LVBench: An Extreme Long Video Understanding Benchmarkcited by 402
  3. 2024VideoAgent: Long-form Video Understanding with Large Language Model as Agentcited by 323
  4. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
  5. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  6. 2024VideoAgent: A Memory-augmented Multimodal Agent for Video Understandingcited by 224
  7. 2024Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understandingcited by 210
  8. 2024ColPali: Efficient Document Retrieval with Vision Language Modelscited by 190
  9. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 144
  10. 2024HourVideo: 1-Hour Video-Language Understandingcited by 110
  11. 2023Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labellingcited by 87
  12. 2023MM-VID: Advancing Video Understanding with GPT-4V(ision)cited by 82
  13. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 78
  14. 2024DrVideo: Document Retrieval Based Long Video Understandingcited by 63
  15. 2024Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Mannercited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 30; 2026: 46.

76 papers.

Sort:

By area:

  1. 2025WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoningcited by 50
  2. 2025Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generationcited by 42
  3. 2025Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agentscited by 42
  4. 2025Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understandingcited by 30
  5. 2026Agentic Very Long Video Understandingcited by 19
  6. 2025RAG-Anything: All-in-One RAG Frameworkcited by 18
  7. 2025FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusioncited by 15
  8. 2025Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generationcited by 15
  9. 2025AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understandingcited by 14
  10. 2026LensWalk: Agentic Video Understanding by Planning How You See in Videoscited by 14
  11. 2025WikiVideo: Article Generation from Multiple Videoscited by 13
  12. 2025See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Modelcited by 13
38 more
  1. 2025MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystackscited by 11
  2. 2025ReMoMask: Retrieval-Augmented Masked Motion Generationcited by 11
  3. 2025VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoningcited by 11
  4. 2025Video-Browser: Towards Agentic Open-web Video Browsingcited by 9
  5. 2025Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-incited by 8
  6. 2026Hierarchical Long Video Understanding with Audiovisual Entity Cohesion and Agentic Searchcited by 8
  7. 2026Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisitioncited by 8
  8. 2026Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understandingcited by 8
  9. 2025AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoningcited by 7
  10. 2026Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanismcited by 7
  11. 2025SceneRAG: Scene-level Retrieval-Augmented Generation for Video Understandingcited by 6
  12. 2025MARC: Memory-Augmented RL Token Compression for Efficient Video Understandingcited by 6
  13. 2026LongVideo-R1: Smart Navigation for Low-cost Long Video Understandingcited by 6
  14. 2026MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Controlcited by 6
  15. 2025HKRAG: Holistic Knowledge Retrieval-Augmented Generation Over Visually-Rich Documentscited by 5
  16. 2026Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoningcited by 5
  17. 2026VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAGcited by 5
  18. 2026VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authoritycited by 5
  19. 2026VideoAgent: All-in-One Framework for Video Understanding and Editingcited by 5
  20. 2025Venus: An Efficient Edge Memory-and-Retrieval System for VLM-based Online Video Understandingcited by 4
  21. 2026SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaborationcited by 4
  22. 2026Towards Fast and Effective Long Video Understanding of Multimodal Large Language Models via Adaptive Quasi-Gaussian Samplingcited by 4
  23. 2025LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understandingcited by 3
  24. 2025Reasoning Text-to-Video Retrieval via Digital Twin Video Representations and Large Language Modelscited by 3
  25. 2026Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understandingcited by 3
  26. 2026EgoGraph: Temporal Knowledge Graph for Egocentric Video Understandingcited by 3
  27. 2026FileGram: Grounding Agent Personalization in File-System Behavioral Tracescited by 3
  28. 2026Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoningcited by 3
  29. 2026SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memorycited by 3
  30. 2026Watch, Remember, Reason: Human-View Video Understanding with MLLMscited by 3
  31. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  32. 2025CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generationcited by 2
  33. 2025Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Surveycited by 2
  34. 2026Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioningcited by 2
  35. 2026Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoningcited by 2
  36. 2025RAVID: Retrieval-Augmented Visual Detection: A Knowledge-Driven Approach for AI-Generated Image Identificationcited by 1
  37. 2025Spatiotemporal Knowledge Graphs as Persistent Scene Memory for Embodied Question Answeringcited by 1
  38. 2025Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generationcited by 1

50 most cited of 76 All 76 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025VideoRAG: Retrieval-Augmented Generation over Video Corpus
  2. 2025E-VRAG: Enhancing Long Video Understanding with Resource-Efficient Retrieval Augmented Generation
  3. 2025Towards Effective Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval
  4. 2026EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding
  5. 2026LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation
  6. 2026Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retrieval-Augmented Generation
  7. 2025UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities
  8. 2025TV-RAG: A Temporal-aware and Semantic Entropy-Weighted Framework for Long Video Retrieval and Understanding