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
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.
Related papers
- MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic EnvironmentsFebruary 3, 2026 · arXiv
- BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking MechanismMay 27, 2025 · EMNLP 2025 (Oral)
- ReachAgent: Enhancing Mobile Agent via Page Reaching and OperationApril 30, 2025 · NAACL 2025 (Poster)
- LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration BenchmarkApril 18, 2025 · arXiv
- META-GUI: Towards Multi-modal Conversational Agents on Mobile GUIMay 23, 2022 · EMNLP 2022
- WebATLAS: An LLM Agent with Experience-Driven Memory and Action SimulationOctober 26, 2025 · NeurIPS 2025 Workshop on Language Agents and World Models