Подход к анализу видео, который адаптивно выбирает наиболее релевантные для задачи фрагменты и сигналы, такие как кадры, аудио или расшифрованный текст.
Google has added “agentic video understanding” to Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite, allowing the model to determine which sections and media it needs to examine instead of processing video at a fixed frame rate. The company says the feature reduces token consumption by up to 88% and costs by up to 66%, while improving accuracy by up to 7%.