AI操作电脑：不看屏幕，直接读代码
现在的AI操作电脑，都是先截图、再识别、再点击——但截图会丢失信息，比如文件内容、后台状态。这篇论文反其道而行：让AI直接通过代码读取程序状态（文件、DOM等），只在需要点击时才用截图。结果：成功率从20.6%提升到26.9%，成本却降到原来的1/9。更关键的是，它揭示了一个反直觉的事实：AI操作电脑的瓶颈不是“看不清”，而是“想不明白”。这不是你明天能用的工具，但它指明了方向：未来AI助手可能不再需要“看”你的屏幕。
📄 原文摘要(英文)
Computer-use agents are usually improved by strengthening perception: better models for reading a screenshot and choosing where to click. Yet a screenshot is only a lossy rendering of the underlying program state, e.g., the files, application backends, and DOM that hold the task data. Different states can produce the same pixels, while code can inspect and modify that state directly. StateAct is a code-first, multi-agent harness built around this distinction. Its main agent works directly with program state by using code, while a dedicated GUI subagent handles screenshot-and-click interaction on the few subgoals that need it, just 28 of 108 tasks and 1.1% of main-agent steps. The same direct access to program state also supports verification: an independent finish gate double-checks the saved result for structural failures, e.g., output that is missing, unsaved, or written to the wrong path. To stay on track over hundreds of steps, the main agent hands subgoals to fresh subagents, keeping its own context focused. On OSWorld 2.0, StateAct lifts Claude Opus 4.8 from 20.6% to 26.9% on binary success, and from 54.8% to 61.6% on partial success, at ~ 9x lower cost per task than the same model driven by screenshots alone; a code-only variant with no GUI subagent reaches only 45.9% partial, below that screenshot-based baseline's 54.8%. In general, grounding action, verification, and memory in state, what we call state-grounding, shifts the main bottleneck from perception toward reasoning: failures depend more on what the agent thinks than on what it sees.