OpenMobile-2 用 110+ 应用训练环境证明开源手机智能体可媲美闭源模型
OpenMobile-2 proves open-source smartphone agents can rival proprietary models
搞手机智能体的可以看看：OpenMobile-2 用 110 多个应用做训练环境，开源里跑分第一，还公开了环境搭建思路。
OpenMobile-2 的研究团队发现，手机智能体的提升关键在于覆盖尽可能多的不同应用，而非堆数据。他们搭建了一个包含 110 多个应用的开放训练环境，其中有 35 个热门应用的复刻版本。在真实 Android 设备测试中，OpenMobile-2 在开源智能体中取得最高分，作者称其表现可以与闭源模型抗衡。
OpenMobile-2 proves open-source smartphone agents can rival proprietary models
Smartphone agents don't get better by processing more data. They improve by training on as many different apps as possible. The researchers behind OpenMobile-2 built an open training environment with more than 110 applications, including 35 replicas of popular apps. On real Android devices, their model scores highest among open agents, the authors say. The article OpenMobile-2 proves open-source smartphone agents can rival proprietary models appeared first on The Decoder .
