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 (24)
- Not All Graphs Are Maps: A Task-Agnostic Exploration Framework for Mobile GUI NavigationOctober 15, 2026 · arXiv
- MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent ResearchMay 25, 2026 · arXiv
- ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental SynthesisMay 24, 2026 · arXiv
- 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
- A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software EvolutionOctober 11, 2026 · arXiv
- 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
- WebWalker: Benchmarking LLMs in Web TraversalJanuary 13, 2025 · arXiv
- The BrowserGym Ecosystem for Web Agent ResearchDecember 6, 2024 · TMLR
- SheetCopilot: Bringing Software Productivity to the Next Level through Large Language ModelsMay 30, 2023 · NeurIPS 2023
- Grounding Open-Domain Instructions to Automate Web Support TasksMarch 30, 2021 · NAACL 2021
- iPrefBench: A User-Centric Benchmark for Personalized Mobile Use AgentsOctober 26, 2026 · arXiv
- AndroidFlux: Evaluating Failure Recovery and Recovery Action Reward Modeling in Mobile-Use Multimodal AgentsOctober 25, 2026 · arXiv
- MobileJailBench: Red Queen Jailbreak Benchmarking for Mobile AgentsOctober 16, 2026 · arXiv
- MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency InjectionOctober 16, 2026 · arXiv
- MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer EnvironmentsOctober 14, 2026 · arXiv
- How GUI Agents Fail: GraceBench for Execution Stability DiagnosisOctober 14, 2026 · arXiv
- OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native ToolsOctober 9, 2026 · arXiv
- Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User InterfacesOctober 6, 2026 · arXiv
- Same Tasks, Different Apps: Why Mobile GUI Agents Fail to Generalize?September 28, 2026 · Findings of EMNLP 2026
- MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory LearningSeptember 19, 2026 · USENIX Security 2026