VisualClaw: A Real-Time, Personalized Agent for the Physical World
- Published
- Source
- arXiv
- Paper number
- 441
- Field
- Computer Vision
- arXiv ID
- 2606.16295
Key points
- A cascade gate made of perceptual hash, a 128-dimensional CPU encoder, and an adaptive change gate compresses one hour of streaming video into only 5 to 20 API calls.
- Hot and cold top-k skill injection prevents prompt cost from exploding as the skill bank grows.
- An offline evolver based on failures automatically updates memory and the skill bank, achieving self-evolution without weight updates.
- Across four video-QA benchmarks, it cuts API cost by an average of 98 percent and raises accuracy by an average of 3.85 percent, with EgoSchema peaking at +15.80 percent.
- It builds VisualClawArena with 200 scenarios, supporting workspace-style agent evaluation through a five-stage curation pipeline.
- With Codex, macro accuracy rises by 2.9 percent for GPT-5.5 and by 3.2 percent for Claude Code Sonnet 4.6, while cost falls by 9.5 percent.
Paper links
External research summaries. These are not HDATF publications or measured product results.