手机系统为AI代理重写：任务完成率+21%，成本减半
你的手机系统是为“人点App”设计的，但AI代理（能自动订餐、查日程、填表单的智能体）跑在上面就像穿小鞋——慢、贵、还不安全。这篇论文直接改写了Android底层，把AI代理当成系统的一等公民：给它专属的快捷接口（不用模拟点击，直接调功能）、安全隔离（不让代理乱翻你的相册）、还能按需组合服务（比如订餐时自动调日历和地图）。实测任务完成率涨了21%，token成本降了51%。它不是你明天就能装上的ROM，但指明了未来手机系统该长什么样——不是给你滑的，是给AI替你滑的。
📄 原文摘要(英文)
AI agents are driving a new software paradigm, with the ability to autonomously call tools, extract information, manage memory, and complete tasks that span applications and data sources. Most existing end-user operating systems, however, are designed for application-centric workflows and offer little native support for AI agents. This mismatch limits the wider adoption of agents and leads to execution overhead and safety risks when running agents on conventional systems. While the concept of agent-native operating systems is emerging, the research community lacks an open testbed to explore the architectural primitives desired for agent-mediated interaction. We present AOHP (Android Open Harness Project), an OS-level agent harness built on the Android Open Source Project (AOSP). The core design principle of AOHP is to treat agents as first-class OS actors, enabling adaptive user interfaces and agent-friendly runtime environments. AOHP preserves the mature Android software and hardware ecosystem while introducing three agent-oriented system mechanisms: personalized service composition, efficient agent interfaces, and secure information flow. Based on preliminary experiments on challenging tasks covering key capabilities of OS agents, AOHP shows clear advantages in task completion (+21.12% completion rate), execution cost (-51.55% token cost), and security-policy compliance.