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 superv
An online reinforcement learning framework trains UI navigation agents on live mobile apps using a planning agent, UI grounding model, and a novel neighbor-conditioned value estimation method to improve robustness and reduce inference costs.
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 execution and an inability to recover from errors. To address these limitations, we propose a novel online reinforcement learning framework that trains UI navigation agents directly on live iOS applications. Our framework decouples the agent into two specialized components: a Planning agent and a UI Grounding model. We rely on an LLM-as-a-Judge to provide comprehensive reward…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps was first seen on Hugging Face · Daily papers on Oct 30, 2026. Since then it has appeared in 32 checks on 4 different days. Its best position was #24 of 30, reached on Nov 2, 09:28 UTC. It dropped off the list after Nov 2, 13:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 2, 13:28 UTC, after 4 days of trending.
#24 on Hugging Face · Daily papers, on Nov 2, 09:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Oct 30, 2026 and has been on the list on 4 days (32 checks) since.