Qwen 推出 Qwen Intelligence，三个智能体接管手机操作
Qwen 搞了三个手机智能体，能跨 App 帮你干活，官方说成功率 90%，比 Apple Intelligence 那种浅整合走得更深。
Qwen 发布 Qwen Intelligence，包含三个面向手机端任务的智能体。Planner 负责把请求拆解为步骤，Mobile-Use Agent 负责跨应用执行，能用应用接口就用接口，不行就模拟点按屏幕，官方称端到端成功率达 90%。Creative Agent 可以把一句话在约 3 秒内生成一张成品图片。相比之下，Apple Intelligence 和 Google Gemini 在手机上的整合表现一般，Qwen 的方案指向 AI 与操作系统更深层的结合。
This is an interesting take from Qwen. They launched Qwen Intelligence, three AI agents built to get things done on a smartphone.
A Planner breaks a request into steps, a Mobile-Use Agent carries them out across apps, using app interfaces where it can and tapping the screen where it must, with a reported 90% end-to-end success rate, and a Creative Agent turns one sentence into a finished image in about 3 seconds.
Currently, Apple Intelligence and Google's Gemini are integrated into smartphones and work "okay," but this would be the next big step toward truly integrating AI deeply into the operating system. And frankly, that's one of the biggest weaknesses so far. Running AI models completely at the edge requires small models that are also good enough. And we haven't quite reached that yet.
