Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps
While frontier vision-language models demonstrate strong capabilities in user interface (UI) navigation, their high inference costs prohibit everyday use. Conversely, smaller models trained via supervised fine-tuning (SFT) or offline reinforcement learning often memorize static trajectories, leading to brittle executio...
Pei-Tong Duan, Khashayar Gatmiry, Jeffrey Nichols et al.
· 0 citations