Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool use, but scaling this success to GUI agents remains challenging due to the high cost of interactive environments and the scarcity of realistic training tasks. We introduce MAI-Gym, an open all-in-one pl...
Pan-Rong Tong, Qu-Yu Kong, Peng-Xiang Li et al.· 0 citations
This work introduces hybrid interaction, using deeplinks for direct navigation and GUI actions for other on-screen operations and fallback, and introduces GUI-Hopper, a improves task success in commercial applications on real devices, further demonstrating the benefits of hybrid interaction.
Yu-Chen Sun, Cheng-Lin Cai, Gong-Jie Zhang et al.· 0 citations
Qwen-UI-Agent is presented, a real-world centric foundation GUI agent spanning mobile, computer-use, web, and DeepSearch environments, that sets state-of-the-art performance on mobile-use benchmarks while delivering competitive performance on computer- and browser-use tasks against frontier models.
