高效能電腦使用代理訓練

Efficient Agent Training for Computer Use

May 20, 2025

作者: Yanheng He, Jiahe Jin, Pengfei Liu

cs.AI

摘要

擴展高品質的軌跡數據長期以來一直是開發類人計算機使用代理的關鍵瓶頸。我們引入了PC Agent-E，這是一個高效的代理訓練框架，顯著減少了對大規模人類示範的依賴。僅從312條人工標註的計算機使用軌跡出發，我們通過使用Claude 3.7 Sonnet合成多樣化的行動決策，進一步提升了數據質量。在這些豐富的軌跡上訓練後，我們的PC Agent-E模型在WindowsAgentArena-V2（我們同時發布的改進基準）上取得了顯著的141%相對提升，超越了具有延長思考能力的強大Claude 3.7 Sonnet。此外，PC Agent-E在OSWorld上展現出對不同操作系統的強大泛化能力。我們的研究表明，強大的計算機使用能力可以從少量高質量的軌跡數據中被激發出來。

English

Scaling up high-quality trajectory data has long been a critical bottleneck for developing human-like computer use agents. We introduce PC Agent-E, an efficient agent training framework that significantly reduces reliance on large-scale human demonstrations. Starting with just 312 human-annotated computer use trajectories, we further improved data quality by synthesizing diverse action decisions with Claude 3.7 Sonnet. Trained on these enriched trajectories, our PC Agent-E model achieved a remarkable 141% relative improvement, surpassing the strong Claude 3.7 Sonnet with extended thinking on WindowsAgentArena-V2, an improved benchmark we also released. Furthermore, PC Agent-E demonstrates strong generalizability to different operating systems on OSWorld. Our findings suggest that strong computer use capabilities can be stimulated from a small amount of high-quality trajectory data.