STEVE: A Step Verification Pipeline for Computer-use Agent Training
This work addresses the scalability problem in computer-use agent training for AI researchers and developers, offering an incremental improvement over existing methods.
The paper tackles the challenge of training AI agents to autonomously manipulate graphical user interfaces by introducing STEVE, a step verification pipeline that uses GPT-4o to label trajectory steps and Kahneman and Tversky Optimization, resulting in a 7B vision-language model achieving leading performance in the WinAgentArena benchmark with reduced cost.
Developing AI agents to autonomously manipulate graphical user interfaces is a long challenging task. Recent advances in data scaling law inspire us to train computer-use agents with a scaled instruction set, yet using behavior cloning to train agents still requires immense high-quality trajectories. To meet the scalability need, we designed STEVE, a step verification pipeline for computer-use agent training. First, we establish a large instruction set for computer-use agents and collect trajectory data with some suboptimal agents. GPT-4o is used to verify the correctness of each step in the trajectories based on the screens before and after the action execution, assigning each step with a binary label. Last, we adopt the Kahneman and Tversky Optimization to optimize the agent from the binary stepwise labels. Extensive experiments manifest that our agent outperforms supervised finetuning by leveraging both positive and negative actions within a trajectory. Also, STEVE enables us to train a 7B vision-language model as a computer-use agent, achieving leading performance in the challenging live desktop environment WinAgentArena with great efficiency at a reduced cost. Code and data: https://github.com/FanbinLu/STEVE.