Gemini 推出智能体视频理解，大幅降低视频分析成本
原标题：Introducing agentic video understanding with Gemini
AI 摘要
Google DeepMind 发布了 Gemini 3.7 Flash、3.6 Flash 和 3.5 Flash-Lite 的智能体视频理解功能，该功能通过原生视频工具动态搜索和检查视频片段，相比静态处理可降低高达 88% 的 token 消耗和 66% 的成本，同时准确率提升最高 7%。该功能现已通过 Gemini API 在 Google AI Studio 和 Gemini Enterprise Agent Platform 提供，并计划推广到 Gemini 应用和 YouTube 的 'Ask YouTube' 功能。
正文节选
Introducing agentic video understanding with Gemini Today, we’re launching agentic video understanding across our latest models: Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite. This new capability improves accuracy while dramatically reducing token usage and costs for video analysis. Similar to agentic vision, which combines code execution with Gemini models’ native image understanding, agentic video understanding uses Gemini’s native video tools to improve performance and unlock new capabilitie