AutoDroid: LLM-powered Task Automation in Android
Hao Wen, Yuanchun Li, Guohong Liu, Shanhui Zhao, Tao Yu, Toby Jia-Jun Li, Shiqi Jiang, Yunhao Liu, Yaqin Zhang, Yunxin Liu
- 🏛 Institutions
- Tsinghua, Harbin Institute of Technology, University of Notre Dame, MSR Asia
- 📅 Date
- August 29, 2023
- 📑 Publisher
- MobiCom 2024
- 💻 Env
- Mobile
- 🔑 Keywords
TLDR
AutoDroid is an Android task-automation framework that combines LLM commonsense with app-specific knowledge collected through automated dynamic analysis. It introduces functionality-aware UI representations and exploration-based memory injection, and evaluates the system on a 158-task benchmark for memory-augmented Android automation.
Related papers
- GUITester: Enabling GUI Agents for Exploratory Defect DiscoveryJanuary 8, 2026 · arXiv
- GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI AgentMay 22, 2025 · ACL 2025
- LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration BenchmarkApril 18, 2025 · arXiv
- You Only Look at Screens: Multimodal Chain-of-Action AgentsSeptember 20, 2023 · Findings of ACL 2024
- LongHorizonUI: A Unified Framework for Robust long-horizon Task Automation of GUI AgentJanuary 26, 2026 · ICLR 2026 (Poster)
- WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting PointFebruary 12, 2025 · arXiv