MobiAgent提升移动端智能代理的准确率与效率。
MobiAgent: A Systematic Framework for Customizable Mobile Agents
- 构建三组件系统：MobiMind模型、AgentRR加速框架、MobiFlow基准测试套件。
- 相比通用大模型与专用GUI代理，实测表现达当前最优水平。
- 引入AI辅助数据采集，大幅降低人工标注成本，解决数据瓶颈。
随着视觉-语言模型（VLMs）的快速发展，基于GUI的移动代理已成为智能移动系统的重要发展方向。然而，现有代理模型在真实场景任务执行中仍面临准确性与效率的显著挑战。为应对这些限制，我们提出MobiAgent，一个包含三大核心组件的综合移动代理系统：MobiMind系列代理模型、AgentRR加速框架以及MobiFlow基准测试套件。此外，鉴于当前移动代理能力受限于高质量数据的获取，我们开发了一种AI辅助的敏捷数据收集管道，显著降低了人工标注成本。相较于通用大语言模型（LLMs）和专用GUI代理模型，MobiAgent在真实移动场景中实现了最先进的性能表现。
原文摘要 · Abstract (English)
With the rapid advancement of Vision-Language Models (VLMs), GUI-based mobile agents have emerged as a key development direction for intelligent mobile systems. However, existing agent models continue to face significant challenges in real-world task execution, particularly in terms of accuracy and efficiency. To address these limitations, we propose MobiAgent, a comprehensive mobile agent system comprising three core components: the MobiMind-series agent models, the AgentRR acceleration framework, and the MobiFlow benchmarking suite. Furthermore, recognizing that the capabilities of current mobile agents are still limited by the availability of high-quality data, we have developed an AI-assisted agile data collection pipeline that significantly reduces the cost of manual annotation. Compared to both general-purpose LLMs and specialized GUI agent models, MobiAgent achieves state-of-the-art performance in real-world mobile scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。