Back to papers
March 19, 2026cs.AIIntermediate
OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards
Zehao Li, Zhenyu Wu, Yibo Zhao, Bowen Yang, Jingjing Xie, Zhaoyang Liu, Zhoumianze Liu, Kaiming Jin, Jianze Liang, Zonglin Li, Feng Wu, Bowen Zhou, Zun Wang, Zichen Ding
AI-Generated Summary
OS-Themis is a new framework that helps train AI agents to better interact with graphical user interfaces (like phone apps) by providing more reliable feedback on whether the agent is performing tasks correctly. Instead of using a single judge, it breaks down agent actions into verifiable milestones and cross-checks the evidence before making a decision, similar to how a court system works. When tested on smartphone tasks, this approach improved performance by about 10% during training and 7% when filtering practice data.
Difficulty
Intermediate
Categories
cs.AI
AI Tags
reinforcement learningGUI agentsreward functionsmulti-agent systemsbenchmark