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

Zichen Zhu , Hao Tang , Yansi Li , Dingye Liu , Hongshen Xu , Kunyao Lan , Danyang Zhang , Yixuan Jiang , Hao Zhou , Chenrun Wang , Situo Zhang , Liangtai Sun , Yixiao Wang , Yuheng Sun , Lu Chen , Kai Yu

🏛 Institutions: SJTU AI Institute , SJTU
📅 Date: April 30, 2025
📑 Publisher: NAACL 2025 (System Demonstrations)
💻 Env: Mobile
🔑 Keywords: framework dataset memory adaptive planning MobBench MobA

TLDR

MobA is a mobile assistant system for complex GUI tasks in dynamic app contexts where execution capabilities vary across pages. It combines reflection-based adaptive planning with a multifaceted memory module, and introduces the MobBench dataset for complex mobile interactions alongside results on MobBench and AndroidArena.

Open paper Code Report issue