MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation

TL;DR

MobA is a novel mobile assistant system that leverages adaptive planning, reflection, and multifaceted memory to improve handling of complex GUI interactions and task automation on mobile devices.

Contribution

MobA introduces a multifaceted memory module and an adaptive planning mechanism with reflection for error recovery, advancing mobile task automation capabilities.

Findings

MobA outperforms baselines on MobBench and AndroidArena datasets.

The system effectively manages dynamic GUI environments.

MobA demonstrates improved task success rates and adaptability.

Abstract

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.