Pith. sign in

REVIEW 16 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.01549 v1 pith:SJP4TDVZ submitted 2025-02-03 cs.IR cs.AIcs.CV

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

classification cs.IR cs.AIcs.CV
keywords videoragvideosknowledgegenerationmulti-modalretrieval-augmentedlong-contextsemantic
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory

    cs.CV 2026-05 unverdicted novelty 7.0

    SuperMemory-VQA provides 4,853 human-verified QA pairs from 52.9 hours of egocentric AI glasses recordings to benchmark AI systems on realistic long-horizon memory tasks including an unanswerable option.

  2. SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration

    cs.CV 2026-04 unverdicted novelty 7.0

    SVAgent improves long video question answering by constructing storylines via multi-agent collaboration and aligning cross-modal predictions for more robust, human-like reasoning.

  3. DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing

    cs.CV 2026-04 unverdicted novelty 7.0

    DIRECT uses a three-level multi-agent framework to solve video mashup creation as a multimodal coherency problem, outperforming baselines on a new benchmark.

  4. LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding

    cs.CV 2026-02 unverdicted novelty 7.0

    LongVideo-R1 trains a reasoning agent on 33K trajectories to intelligently select informative video clips via iterative refinement and RL, achieving better accuracy-efficiency tradeoffs on long video QA benchmarks.

  5. M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation

    cs.CL 2025-12 unverdicted novelty 7.0

    M³KG-RAG improves multimodal reasoning in large language models by constructing multi-hop knowledge graphs and selectively pruning retrieved context with GRASP.

  6. VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement

    cs.CV 2026-07 unverdicted novelty 6.0

    VideoSearch-R1 achieves SOTA on VCMR across three datasets via iterative retrieval, latent-space soft query refinement, and GRPO training.

  7. Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios

    cs.AI 2026-05 unverdicted novelty 6.0

    Event-Causal RAG segments videos into events represented as SES graphs, merges them into a causal knowledge graph, and uses bidirectional retrieval to supply relevant event chains to a video foundation model for impro...

  8. MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control

    cs.CV 2026-04 unverdicted novelty 6.0

    MMEmb-R1 adaptively applies chain-of-thought reasoning to multimodal embeddings via pair-aware counterfactual selection and RL, reaching 71.2 on MMEB-V2 with a 4B model and lower latency.

  9. VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG

    cs.CV 2026-04 unverdicted novelty 6.0

    VideoStir introduces a spatio-temporal graph-based structure and intent-aware retrieval for long-video RAG, achieving competitive performance with SOTA methods via a new IR-600K dataset.

  10. FileGram: Grounding Agent Personalization in File-System Behavioral Traces

    cs.CV 2026-04 unverdicted novelty 6.0

    FileGram grounds AI agent personalization in file-system behavioral traces via a data simulation engine, a diagnostic benchmark, and a bottom-up memory architecture.

  11. Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning

    cs.CV 2026-04 unverdicted novelty 6.0

    G2F-RAG converts retrieved knowledge subgraphs into a single visual reasoning frame appended to videos, enabling training-free and interpretable improvements for LMM-based video reasoning on knowledge-intensive tasks.

  12. Reason Before You Retrieve: Agentic Planning for Multi-modal RAG

    cs.AI 2026-06 reject novelty 5.0

    MM-R2 claims SOTA multimodal RAG accuracy on InfoSeek and Encyclopedic VQA via intent grounding plus a 10-topic KnowledgeMap, but its teacher trajectories leak the gold Wikipedia page and omit the image.

  13. Towards Fast and Effective Long Video Understanding of Multimodal Large Language Models via Adaptive Quasi-Gaussian Sampling

    cs.CV 2026-06 unverdicted novelty 5.0

    AdaQ is a training-free adaptive quasi-Gaussian sampling method for keyframe selection that improves long-video understanding in MLLMs and can outperform GPT-4o with 64 frames.

  14. UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks

    cs.CV 2026-04 unverdicted novelty 5.0

    UpstreamQA disentangles video reasoning by using LRMs for explicit upstream object identification and scene context before downstream LMM VideoQA, improving performance and interpretability on OpenEQA and NExTQA in so...

  15. SafeScreen: A Safety-First Screening Framework for Personalized Video Retrieval for Vulnerable Users

    cs.CV 2026-03 unverdicted novelty 5.0

    SafeScreen enforces individualized safety constraints as a prerequisite for video retrieval by using profile extraction, adaptive VideoRAG analysis, and LLM decision-making to approve content for vulnerable users.

  16. Watch, Remember, Reason: Human-View Video Understanding with MLLMs

    cs.CV 2026-06 unverdicted novelty 4.0

    This is a survey that frames video MLLM research via a human-view formulation of perceptual representations, memory states, reasoning traces, and predictions, then reviews methods, datasets, benchmarks, and open problems.