Hugging Peers

PAGE: Progress-Aware Reinforcement Learning with Hierarchical Advantage for Long-Horizon GUI Agents

☆ Save
Zhang, Qingliang,Sun, Yongqian,Cai, Yuanhong,Nie, Xiaohui,Wang, JiaJu,Luo, Yu,Jiang, Jiamin,Chen, Zhekang
+5 more authors show fewer
Fang, Yaozheng,Wang, Meng,Xian, Chaobo,Li, Peng,Pei, Dan
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
published

Abstract

No abstract available.

Cite this paper

@article{qingliang2026,
  title = {PAGE: Progress-Aware Reinforcement Learning with Hierarchical Advantage for Long-Horizon GUI Agents},
  author = {Zhang, Qingliang and Sun, Yongqian and Cai, Yuanhong and Nie, Xiaohui and Wang, JiaJu and Luo, Yu and Jiang, Jiamin and Chen, Zhekang and Fang, Yaozheng and Wang, Meng and Xian, Chaobo and Li, Peng and Pei, Dan},
  journal = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year = {2026},
  month = {Jan},
}