Stacked video agents often lose to plain inference: SAVE matches native Gemini 3 Flash on Minerva at about 60% of the cost
In a controlled evaluation that fixes the backbone to Gemini 3 Flash or Gemma 4 and accounts for tokens and cost, most existing agentic video-reasoning frameworks fail to consistently beat native inference and often cost more. SAVE keeps the simplest interaction loop and only changes the query unit from a single frame to a time range, adapting scene detection and visual resolution to the range length. On Minerva with Gemini 3 Flash, SAVE reaches 66.4% accuracy, comparable to 64.8% for native inference, while cutting inference cost by about 60%.