Apple ML Research Publishes Online RL Framework for iOS UI Navigation
Apple proposes a new online RL method for training UI agents, showing 8B models outperform SFT baselines and rival frontier models in cross-platform generalization.
Apple's Machine Learning Research team published a paper in November 2026 proposing a novel online reinforcement learning (RL) framework for training user interface (UI) navigation agents directly on live iOS applications.
The framework decouples the agent into a Planning agent and a UI Grounding model, introducing GiGPPO, a neighbor-conditioned value estimation method to improve critic stability. Evaluations show that 8B parameter agents trained with this online RL approach achieved nearly a sevenfold improvement over supervised fine-tuning (SFT) baselines in out-of-distribution generalization to Android environments, while outperforming Gemini-3.5-Flash and tying with Gemini-3.1-Pro on real iOS applications.