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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Zichen, Tang, Hao, Li, Yansi, Liu, Dingye, Xu, Hongshen, Lan, Kunyao, Zhang, Danyang, Jiang, Yixuan, Zhou, Hao, Wang, Chenrun, Zhang, Situo, Sun, Liangtai, Wang, Yixiao, Sun, Yuheng, Chen, Lu, Yu, Kai
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915604907163648
author Zhu, Zichen
Tang, Hao
Li, Yansi
Liu, Dingye
Xu, Hongshen
Lan, Kunyao
Zhang, Danyang
Jiang, Yixuan
Zhou, Hao
Wang, Chenrun
Zhang, Situo
Sun, Liangtai
Wang, Yixiao
Sun, Yuheng
Chen, Lu
Yu, Kai
author_facet Zhu, Zichen
Tang, Hao
Li, Yansi
Liu, Dingye
Xu, Hongshen
Lan, Kunyao
Zhang, Danyang
Jiang, Yixuan
Zhou, Hao
Wang, Chenrun
Zhang, Situo
Sun, Liangtai
Wang, Yixiao
Sun, Yuheng
Chen, Lu
Yu, Kai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13757
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation
Zhu, Zichen
Tang, Hao
Li, Yansi
Liu, Dingye
Xu, Hongshen
Lan, Kunyao
Zhang, Danyang
Jiang, Yixuan
Zhou, Hao
Wang, Chenrun
Zhang, Situo
Sun, Liangtai
Wang, Yixiao
Sun, Yuheng
Chen, Lu
Yu, Kai
Multiagent Systems
Artificial Intelligence
Computation and Language
Human-Computer Interaction
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.
title MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation
topic Multiagent Systems
Artificial Intelligence
Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2410.13757