谷歌推 StreamVibe 视频智能体，可自主判断何时提供帮助
原标题：Google wants video AI to understand what people need as they work
AI 摘要
谷歌联合斯坦福、牛津等机构的研究团队提出 StreamVibe，一个能自行判断何时开口提供帮助的视频智能体，并基于约4100个样本、183小时日常与软件录屏构建基准测试。团队训练了 StreamVibe-VL 模型（疑似基于阿里 Qwen3.5-9B），结合强化学习与独立记忆系统，使响应时机与质量提升10.7%，主动交互提升12.3%。测试显示所有模型在连续处理长视频并依赖自身历史时性能大幅下降，响应关键指标最多降低61.5%，说明让视频 AI 理解模糊意图并持续跟踪进度仍很困难。
正文节选
Google wants video AI to understand what people need as they work A research team led by Google has introduced StreamVibe, a video agent designed to decide for itself when to speak up. The tests show above all how hard that remains for today's AI models. Researchers from Google, Stanford, Oxford, and several U.S. universities are working on an assistant that watches you cook or assemble furniture and speaks up only when needed. With StreamVibe, they've built a video agent designed to understand