Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Junyang, Xu, Haiyang, Zhang, Xi, Yan, Ming, Zhang, Ji, Huang, Fei, Sang, Jitao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908390705332224
author Wang, Junyang
Xu, Haiyang
Zhang, Xi
Yan, Ming
Zhang, Ji
Huang, Fei
Sang, Jitao
author_facet Wang, Junyang
Xu, Haiyang
Zhang, Xi
Yan, Ming
Zhang, Ji
Huang, Fei
Sang, Jitao
contents The exponential rise in mobile device usage necessitates streamlined automation for effective task management, yet many AI frameworks fall short due to inadequate operational expertise. While manually written knowledge can bridge this gap, it is often burdensome and inefficient. We introduce Mobile-Agent-V, an innovative framework that utilizes video as a guiding tool to effortlessly and efficiently inject operational knowledge into mobile automation processes. By deriving knowledge directly from video content, Mobile-Agent-V eliminates manual intervention, significantly reducing the effort and time required for knowledge acquisition. To rigorously evaluate this approach, we propose Mobile-Knowledge, a benchmark tailored to assess the impact of external knowledge on mobile agent performance. Our experimental findings demonstrate that Mobile-Agent-V enhances performance by 36% compared to existing methods, underscoring its effortless and efficient advantages in mobile automation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13887
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation
Wang, Junyang
Xu, Haiyang
Zhang, Xi
Yan, Ming
Zhang, Ji
Huang, Fei
Sang, Jitao
Artificial Intelligence
Computation and Language
The exponential rise in mobile device usage necessitates streamlined automation for effective task management, yet many AI frameworks fall short due to inadequate operational expertise. While manually written knowledge can bridge this gap, it is often burdensome and inefficient. We introduce Mobile-Agent-V, an innovative framework that utilizes video as a guiding tool to effortlessly and efficiently inject operational knowledge into mobile automation processes. By deriving knowledge directly from video content, Mobile-Agent-V eliminates manual intervention, significantly reducing the effort and time required for knowledge acquisition. To rigorously evaluate this approach, we propose Mobile-Knowledge, a benchmark tailored to assess the impact of external knowledge on mobile agent performance. Our experimental findings demonstrate that Mobile-Agent-V enhances performance by 36% compared to existing methods, underscoring its effortless and efficient advantages in mobile automation.
title Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2505.13887