Do Multi-Agents Dream of Electric Screens? Achieving 100% on AndroidWorld Through Task Decomposition
cs.AI
Submitted: 2026-02-08
Updated: 2026-11-16
Code: https://github.com/minitapai/mobile-use
Terminology
Sources
- Agent S: An Open Agentic Framework that Uses Computers Like a Human
- DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
- Qwen2.5-VL Technical Report
- Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments
- LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark
- Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment
- Achieving the fundamental quantum limit of linear waveform estimation
- ZeroGUI: Automating Online GUI Learning at Zero Human Cost
- UI-Venus Technical Report: Building High-performance UI Agents with RFT
- Seed1.5-VL Technical Report
- AppAgentX: Evolving GUI Agents as Proficient Smartphone Users
- Agent-Initiated Interaction in Phone UI Automation
- OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web
- MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation
- AutoGLM: Autonomous Foundation Agents for GUIs
- AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation
- ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay
- Building a Stable Planner: An Extended Finite State Machine Based Planning Module for Mobile GUI Agent
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents