計算機使用中擴展代理的非凡效能

摘要

電腦使用代理（CUAs）在自動化日常數位任務方面展現出潛力，但其不可靠性與高變異性阻礙了其在長期、複雜任務中的應用。我們引入了行為最佳N選（bBoN）方法，該方法通過生成多個執行路徑並利用描述代理執行路徑的行為敘事進行選擇，從而實現了對代理的擴展。此方法既支持廣泛探索，又基於原則進行軌跡選擇，大幅提升了魯棒性與成功率。在OSWorld平台上，我們的bBoN擴展方法以69.9%的成績創下了新的技術前沿（SoTA），顯著超越先前方法，並接近72%的人類水平表現，全面的消融實驗驗證了關鍵設計選擇的有效性。我們進一步展示了在WindowsAgentArena和AndroidWorld上對不同操作系統的強大泛化能力。關鍵在於，我們的結果凸顯了當方法得當時，擴展CUAs的非凡效果：有效的擴展需要結構化的軌跡理解與選擇，而bBoN提供了一個實用的框架來實現這一目標。

English

Computer-use agents (CUAs) hold promise for automating everyday digital tasks, but their unreliability and high variance hinder their application to long-horizon, complex tasks. We introduce Behavior Best-of-N (bBoN), a method that scales over agents by generating multiple rollouts and selecting among them using behavior narratives that describe the agents' rollouts. It enables both wide exploration and principled trajectory selection, substantially improving robustness and success rates. On OSWorld, our bBoN scaling method establishes a new state of the art (SoTA) at 69.9%, significantly outperforming prior methods and approaching human-level performance at 72%, with comprehensive ablations validating key design choices. We further demonstrate strong generalization results to different operating systems on WindowsAgentArena and AndroidWorld. Crucially, our results highlight the unreasonable effectiveness of scaling CUAs, when you do it right: effective scaling requires structured trajectory understanding and selection, and bBoN provides a practical framework to achieve this.

計算機使用中擴展代理的非凡效能

The Unreasonable Effectiveness of Scaling Agents for Computer Use

摘要

Support