MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation
This addresses the problem of inefficient mobile task automation for users and developers, representing an incremental improvement over existing MLLM-based agents.
The paper tackles the challenge of MLLM-based agents struggling with complex GUI interactions on mobile devices by proposing MobA, which introduces adaptive planning and multifaceted memory modules, achieving improved performance on tasks in dynamic environments as demonstrated on MobBench and AndroidArena datasets.
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.