Existing Multimodal Large Language Model (MLLM)-based agents face significant challenges in handling complex GUI (Graphical User Interface) interactions on devices. These challenges arise from the dynamic and structured nature of GUI environments, which integrate text, images, and spatial relationships, as well as the variability in action spaces across different pages and tasks. To address these limitations, we propose MobA, a novel MLLM-based mobile assistant system. MobA introduces an adaptive planning module that incorporates a reflection mechanism for error recovery and dynamically adjusts plans to align with the real environment contexts and action module's execution capacity. Additionally, a multifaceted memory module provides comprehensive memory support to enhance adaptability and efficiency. We also present MobBench, a dataset designed for complex mobile interactions. Experimental results on MobBench and AndroidArena demonstrate MobA's ability to handle dynamic GUI environments and perform complex mobile tasks.
@article{arxiv.2410.13757,
title = {MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation},
author = {Zichen Zhu and Hao Tang and Yansi Li and Dingye Liu and Hongshen Xu and Kunyao Lan and Danyang Zhang and Yixuan Jiang and Hao Zhou and Chenrun Wang and Situo Zhang and Liangtai Sun and Yixiao Wang and Yuheng Sun and Lu Chen and Kai Yu},
journal= {arXiv preprint arXiv:2410.13757},
year = {2025}
}