Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
By Junyang Wang, Haiyang Xu, Jiabo Ye, Mingshi Yan, Weizhou Shen, Ji Zhang, Fei Huang, Jitao Sang. arXiv.org, 2024
313 citations recorded by the source corpus.
Mobile device agent based on Multimodal Large Language Models (MLLM) is becoming a popular application. In this paper, we introduce Mobile-Agent, an autonomous multi-modal mobile device agent. Mobile-Agent first leverages visual perception tools to accurately identify and locate both the visual and textual elements within the app's front-end interface. Based on the perceived vision context, it then autonomously plans and decomposes the complex operation task, and navigates the mobile Apps through operations step by step. Different from previous solutions that rely on XML files of Apps or mobile system metadata, Mobile-Agent allows for greater adaptability across diverse mobile operating environments in a vision-centric way, thereby eliminating the necessity for system-specific customizations. To assess the performance of Mobile-Agent, we introduced Mobile-Eval, a benchmark for evaluating mobile device operations. Based on Mobile-Eval, we conducted a comprehensive evaluation of Mobile-Agent. The experimental results indicate that Mobile-Agent achieved remarkable accuracy and completion rates. Even with challenging instructions, such as multi-app operations, Mobile-Agent can still complete the requirements. Code and model will be open-sourced at https://github.com/X-PLUG/MobileAgent.
Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/c5db6c2726911b72d534f97bd4d1ed63f6431340
Citations in the corpus
- Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents (2024, unknown): “(Yan et al., 2023; Kim et al., 2023; Wang et al., 2024a; Zheng et al., 2024; Xie et al., 2024).”
- AppAgent: Multimodal Agents as Smartphone Users (2023, unknown): “To gain deeper insights into the vision capabilities of our agent, we conducted an extensive case study using Adobe Lightroom, an image-editing application.”
- A survey on multimodal large language models (2023, unknown): “The image is from [16].”
- MM-LLMs: Recent Advances in MultiModal Large Language Models (2024, unknown): “, WebVoyager (He et al., 2024), Mobile-Agent (Wang et al., 2024b) End-to-end The remaining models are essentially all end-to-end trainable models.”