Google brings agentic video understanding to Gemini
Brought agentic video understanding to Gemini — instead of sampling at a fixed frame rate, the model itself searches for, scans and closely examines the relevant segments. Applied to Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite. Company claims: up to 88% less token consumption, up to 66% lower analysis cost and up to 7% higher accuracy. Turned on by setting processing to agentic in the API settings, at no extra charge. Rollout to the Gemini app and YouTube Ask has only been previewed
Why it matters
Instead of feeding in a long video whole, the model explores it on its own — multimodal input is folded into the agent loop
Source — Primary sources first; secondary reports are labelled “Press”
Officialblog.googlehttps://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-agentic-video-in-gemini/Added in Week 36, 2026 · See that week