Sign up to save your podcasts
Or
Share Efficient Agent Training for Computer Use
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Efficient Agent Training for Computer Use
🤗 Upvotes: 32 | cs.AI, cs.CL, cs.LG
Authors:
Yanheng He, Jiahe Jin, Pengfei Liu
Title:
Efficient Agent Training for Computer Use
Arxiv:
http://arxiv.org/abs/2505.13909v1
Abstract:
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.
View all episodes
By Jingwen Liang, Gengyu Wang🤗 Upvotes: 32 | cs.AI, cs.CL, cs.LG
Authors:
Yanheng He, Jiahe Jin, Pengfei Liu
Title:
Efficient Agent Training for Computer Use
Arxiv:
http://arxiv.org/abs/2505.13909v1
Abstract:
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.