MobileExplorer: Accelerating On-Device Inference for Mobile GUI Agents via Online Exploration
MobileExplorer is a new framework designed to enhance on-device inference for mobile GUI agents. It aims to reduce latency and improve task success rates by utilizing online exploration of UI elements. The framework has shown promising results, decreasing reasoning steps and latency while maintaining performance across various tasks.
- ▪MobileExplorer accelerates on-device inference for vision-based mobile GUI agents.
- ▪The framework reduces average reasoning steps and end-to-end latency by 23%.
- ▪It maintains or improves task success rates by up to 5% on multiple devices.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.26546 (cs) [Submitted on 26 May 2026] Title:MobileExplorer: Accelerating On-Device Inference for Mobile GUI Agents via Online Exploration Authors:Runxi Huang, Liyu Zhang, Shengzhong Liu, Xiaomin Ouyang View a PDF of the paper titled MobileExplorer: Accelerating On-Device Inference for Mobile GUI Agents via Online Exploration, by Runxi Huang and 3 other authors View PDF HTML (experimental) Abstract:Mobile graphical user interface (GUI) agents enable AI models to autonomously operate smartphones on behalf of users. However, most existing systems focus primarily on optimizing task accuracy and rely on cloud-hosted models for inference, which introduces privacy concerns and network-dependent latency.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
