About this paper
VideoNexus separates detailed video perception from evidence-driven planning and reasoning, using perception sub-agents to return compact temporally grounded evidence and achieving higher accuracy at lower cost on long-video benchmarks.
Understanding long videos requires locating evidence, resolving visual details, and integrating observations into an answer. Even when relevant evidence is present, performing these operations within long, dense visual sequences burdens both perception and reasoning. Video agents enable selective inspection, but returning frames to the planner still accumulates visual information in its reasoning context. Delegating perception reduces this burden, yet sparse sampling can miss decisive details, and per-frame descriptions can preserve context growth. We introduce VideoNexus, a training-free framework that separates detailed video perception from evidence-driven planning and reasoning. The…
training-free frameworkvideo agentsplannerperception sub-agentsnative audio-videoindependent contextstemporally grounded evidenceiterative search and verificationstatic ingestionbuilt-in agentic processing
- Upvotes
- 16
- Authors
- 7
- Published
- Nov 16, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
VideoNexus: Video Perception Beyond the Reasoning Context was first seen on Hugging Face · Daily papers on Nov 18, 2026. Since then it has appeared in 12 checks on 2 different days. Its best position was #4 of 30, reached on Nov 19, 07:29 UTC. It dropped off the list after Nov 19, 07:29 UTC.