通过行为叙事比较，让计算机任务代理更稳定高效。
Scaling Agents for Computer Use
- 用行为叙事表示代理执行过程，实现多轮次对比选择
- 在OSWorld上达到72.6%成功率，超越人类表现
- 适合需要高可靠性的自动化任务场景
计算机使用代理（CUAs）有望自动化日常数字任务，但在长周期复杂任务上的表现仍不可靠。单次执行易因微小错误累积导致结果波动。尽管已有研究尝试在单次执行中扩展，但成效有限。通过多轮次执行更具潜力，但有效评估和选择长期行为仍具挑战。本文提出行为判官（BJudge），将代理执行表示为行为叙事，在此层面比较候选行为，显著提升鲁棒性和成功率。利用多轮次策略，BJudge 在 OSWorld 上达到 72.6% 的新状态最优（SoTA）表现，显著超过人类水平（72.36%），并通过全面消融实验验证了关键设计。进一步在 WindowsAgentArena 与 AndroidWorld 上展示强泛化能力。结果表明，正确实现规模化能极大提升 CUAs 效果：关键在于结构化轨迹理解与选择，而 BJudge 提供了实用框架。
原文摘要 · Abstract (English)
Computer-use agents (CUAs) hold promise for automating everyday digital tasks, but their performance on long-horizon, complex problems remains unreliable. Single-rollout execution is brittle, with small errors compounding over time and leading to high variance in outcomes. While prior work has attempted to scale within a single rollout, such approaches have yielded limited gains. Scaling over multiple rollouts offers a more promising alternative but doing so effectively is challenging due to the difficulty of evaluating and selecting among long-horizon agent behaviors. We introduce Behavior Judge (BJudge), which addresses this challenge by representing agent executions as behavior narratives and comparing candidate behaviors at this level, substantially improving robustness and success rates. Using multiple rollouts, BJudge establishes a new state of the art (SoTA) in OSWorld at 72.6%, significantly outperforming prior methods and surpassing human-level performance at 72.36%, 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 strong effectiveness of scaling CUAs, when you do it right: effective scaling requires structured trajectory understanding and selection, and BJudge provides a practical framework to achieve this.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。