analiza aiqbench
This research introduces GUI-Hopper, a system that enhances mobile AI agents by integrating app-native deeplinks to bypass standard tap-and-swipe navigation sequences. By constructing a verified catalog of functional links through static analysis and real-device validation, the approach significantly improves task success rates in commercial applications. The work represents a concrete advancement in agent efficiency, demonstrating how hybrid interaction strategies can optimize GUI automation workflows.
From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks
arXiv:2609.30887v1 Announce Type: new Abstract: Mobile GUI agents complete tasks using GUI actions like taps and swipes. These actions are broadly applicable across applications, but reaching a navigation interface. A single deeplink call can replace a sequence of screen-by-screen GUI actions. We therefore introduce hybrid interaction, using deeplinks for direct navigation and GUI actions for other on-screen operations and fallback. To enable this, we discover candidate deeplinks through static analysis, validate them on real devices, and describe their observed landing screens. This process creates a verified and grounded deeplink catalog that pairs each working deeplink with a description of its landing screen. Using this catalog, we introduce GUI-Hopper, a improves task success in commercial applications on real devices, further demonstrating the benefits of hybrid interaction.
Abstract:Mobile GUI agents complete tasks using GUI actions like taps and swipes. These actions are broadly applicable across applications, but reaching a navigation interface. A single deeplink call can replace a sequence of screen-by-screen GUI actions. We therefore introduce hybrid interaction, using deeplinks for direct navigation and GUI actions for other on-screen operations and fallback. To enable this, we discover candidate deeplinks through static analysis, validate them on real devices, and describe their observed landing screens. This process creates a verified and grounded deeplink catalog that pairs each working deeplink with a description of its landing screen. Using this catalog, we introduce GUI-Hopper, a improves task success in commercial applications on real devices, further demonstrating the benefits of hybrid interaction.
Artificial Intelligence (cs.AI)
arXiv:2609.30887 [cs.AI]
(or arXiv:2609.30887v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.30887 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 214 cuvinte
Subiecte conexe

NVIDIA and Japan Bring Full-Stack AI and Robotics to Every Industry
NVIDIA · 15 iul. 2026

NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · 21 mai 2026

Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · 24 sept. 2026

A shared agentic platform for Wood Mackenzie, on Amazon Bedrock AgentCore
AWS · 17 sept. 2026