MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research

arXiv:2605.26114 · cs.AI, cs.CL · Submitted 2026-05-25 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-05-25

Updated: 2026-09-23

Project page: https://mobilegym.github.io

Terminology

• Benchmark — 26× in this paper · explained in 2 episodes
• Calibration — 15× in this paper · explained in 7 episodes
• GRPO — 10× in this paper · explained in 6 episodes
• Benchmarking — 9× in this paper · explained in 3 episodes
• Verification — 9× in this paper · explained in 2 episodes
• Fidelity — 7× in this paper · explained in 2 episodes
• Robustness — 7× in this paper · explained in 5 episodes
• Success Rate — 7× in this paper
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Unexpected Side Effects — 6× in this paper
• Core — 5× in this paper · explained in 2 episodes
• Generalization — 5× in this paper · explained in 13 episodes
• Action Space — 4× in this paper · explained in 1 episode
• False Complete — 4× in this paper
• Trace — 4× in this paper · explained in 2 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Meeting of the Association for Computational Linguistics — 3× in this paper
• Overdue Termination — 2× in this paper
• Progress Rate — 2× in this paper
• Sim-to-Real Transfer — 2× in this paper · explained in 2 episodes
• Thirteenth International Conference on Learning Representations — 2× in this paper
• Verifier — 2× in this paper · explained in 2 episodes
• World Model — 2× in this paper · explained in 7 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Compositional Generalization — 1× in this paper · explained in 4 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Graph Construction — 1× in this paper · explained in 3 episodes
• Initial Data — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• State Management — 1× in this paper · explained in 3 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes

Sources

• Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System
• WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks
• MVISU-Bench: Benchmarking Mobile Agents for Real-World Tasks by Multi-App, Vague, Interactive, Single-App and Unethical Instructions
• Qwen3-VL Technical Report
• MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments
• GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training
• AutoGLM: Autonomous Foundation Agents for GUIs
• A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation
• ViMo: A Generative Visual GUI World Model for App Agents
• GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
• Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• UI-Venus-1.5 Technical Report
• UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
• MobileBench-OL: A Comprehensive Chinese Benchmark for Evaluating Mobile GUI Agents in Real-World Environment
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines
• MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
• UISim: An Interactive Image-Based UI Simulator for Dynamic Mobile Environments
• ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks

Related papers

• 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
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection