# MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents

arXiv: https://arxiv.org/abs/2509.18119 · HTML: https://mlsanity.com/paper/2509.18119/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 25 of 25)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Android in the Wild: A Large-Scale Dataset for Android Device Control](https://mlsanity.com/paper/2307.10088/) (2023)
- [GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents](https://mlsanity.com/paper/2504.10458/) (2025)
- [Teacher-Student Curriculum Learning](https://mlsanity.com/paper/1707.00183/) (2017)
- [UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning](https://mlsanity.com/paper/2503.21620/) (2025)
- [Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents](https://mlsanity.com/paper/2504.00906/) (2025)
- [AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents](https://mlsanity.com/paper/2410.24024/) (2024)
- [AndroidEnv: A Reinforcement Learning Platform for Android](https://mlsanity.com/paper/2105.13231/) (2021)
- [T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling](https://mlsanity.com/paper/2501.11651/) (2025)
- [MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents](https://mlsanity.com/paper/2406.08184/) (2024)
- [Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents](https://mlsanity.com/paper/2407.00993/) (2024)
- [Benchmarking Mobile Device Control Agents across Diverse Configurations](https://mlsanity.com/paper/2404.16660/) (2024)
- [ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents](https://mlsanity.com/paper/2508.14040/) (2025)
- [Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment](https://mlsanity.com/paper/2503.15937/) (2025)
- [AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation](https://mlsanity.com/paper/2412.18116/) (2024)
- [UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents](https://mlsanity.com/paper/2505.21496/) (2025)
- [UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding](https://mlsanity.com/paper/2507.22025/) (2025)
- [Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage](https://mlsanity.com/paper/2106.03207/) (2021)
- [AndroidGen: Building an Android Language Agent under Data Scarcity](https://mlsanity.com/paper/2504.19298/) (2025)

## Built on by (most cited first, 30 of 43)

- [Step-GUI Technical Report](https://mlsanity.com/paper/2512.15431/) (2025)
- [Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning](https://mlsanity.com/paper/2607.07508/) (2026)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training](https://mlsanity.com/paper/2602.14093/) (2026)
- [CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents](https://mlsanity.com/paper/2607.05378/) (2026)
- [GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?](https://mlsanity.com/paper/2510.20333/) (2025)
- [UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents](https://mlsanity.com/paper/2602.05832/) (2026)
- [ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration](https://mlsanity.com/paper/2509.21823/) (2025)
- [AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management](https://mlsanity.com/paper/2512.10371/) (2025)
- [UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience](https://mlsanity.com/paper/2603.24533/) (2026)
- [Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding](https://mlsanity.com/paper/2605.00642/) (2026)
- [ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents](https://mlsanity.com/paper/2605.12481/) (2026)
- [OpAgent: Operator Agent for Web Navigation](https://mlsanity.com/paper/2602.13559/) (2026)
- [CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation](https://mlsanity.com/paper/2604.09155/) (2026)
- [SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL](https://mlsanity.com/paper/2607.11185/) (2026)
- [Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning](https://mlsanity.com/paper/2601.03641/) (2026)
- [UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics](https://mlsanity.com/paper/2604.02345/) (2026)
- [VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics](https://mlsanity.com/paper/2604.06182/) (2026)
- [What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States](https://mlsanity.com/paper/2606.31612/) (2026)
- [OpenPhone: Mobile Agentic Foundation Models](https://mlsanity.com/paper/2510.22009/) (2025)
- [Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction](https://mlsanity.com/paper/2602.00575/) (2026)
- [BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments](https://mlsanity.com/paper/2603.25747/) (2026)
- [HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents](https://mlsanity.com/paper/2607.14548/) (2026)
- [SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents](https://mlsanity.com/paper/2512.22322/) (2025)
- [GUI Agents with Reinforcement Learning: Toward Digital Inhabitants](https://mlsanity.com/paper/2604.27955/) (2026)
- [EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents](https://mlsanity.com/paper/2607.09773/) (2026)
- [ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis](https://mlsanity.com/paper/2605.25160/) (2026)
- [PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control](https://mlsanity.com/paper/2605.15963/) (2026)
- [PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents](https://mlsanity.com/paper/2605.29486/) (2026)
- [LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control](https://mlsanity.com/paper/2606.16802/) (2026)

## Abstract (arXiv)

Building general-purpose graphical user interface (GUI) agents has become increasingly promising with the progress in vision language models. However, developing effective mobile GUI agents with reinforcement learning (RL) remains challenging due to the heavy-tailed distribution of task difficulty and the inefficiency of large-scale environment sampling. We present an online agentic reinforcement learning framework MobileRL to enhance GUI agents in mobile environments. Its core component is the Difficulty-ADAptive GRPO (ADAGRPO) algorithm. In ADAGRPO, we design difficulty-adaptive positive replay and failure curriculum filtering to adapt the model to different task difficulties. We introduce the shortest-path reward adjustment strategy to reshape rewards concerning the task length in multi-turn agentic tasks. Those strategies jointly stabilize RL training, improve sample efficiency, and generate strong performance across diverse mobile apps and tasks. We apply MOBILERL to two open models (Qwen2.5-VL-7B-Instruct and GLM-4.1V-9B-Base). The resultant MOBILERL-9B model achieves state-of-the-art results in terms of success rates on both AndroidWorld (80.2%) and AndroidLab (53.6%). The MOBILERL framework is open-sourced at: https://github.com/THUDM/MobileRL.