Skip to content
Book Open access

V-Droid: Advancing Mobile GUI Agent Through Generative Verifiers

Mar 2025 · Proceedings of the 32nd Annual International Conference on Mobile Computing and Networking · 2 citations · ⚡ 1 influential · 36 references
Computer Science

Abstract

We propose V-Droid, a mobile GUI task automation agent. Unlike previous mobile agents that utilize Large Language Models (LLMs) as generators to directly generate actions at each step, V-Droid employs LLMs as verifiers to evaluate candidate actions before making final decisions. To realize this novel paradigm, we introduce a comprehensive framework for constructing verifier-driven mobile agents: the discretized action space construction coupled with the prefilling-only workflow to accelerate the verification process, the pair-wise progress preference training to significantly enhance the verifier's decision-making capabilities, and the scalable human-agent joint annotation scheme to efficiently collect the necessary data at scale. V-Droid obtains a substantial task success rate across several public mobile task automation benchmarks: 59.5% on AndroidWorld, 38.3% on AndroidLab, and 49% on MobileAgent-Bench, surpassing existing agents by 5.2%, 2.1%, and 9%, respectively. Furthermore, V-Droid achieves a remarkably low latency of 4.3s per step and 0.7s per decision, which are 6.1× and 32.1× faster compared with existing mobile agents. The source code is available at https://github.com/V-Droid-Agent/V-Droid.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.