MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents
By: Yifan Xu , Xiao Liu , Xinghan Liu and more
Potential Business Impact:
Teaches phones to do tasks by themselves.
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 (75.8%) and AndroidLab (46.8%). The MOBILERL framework is adopted in the AutoGLM products, and also open-sourced at https://github.com/THUDM/MobileRL.
Similar Papers
MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
Machine Learning (CS)
Teaches phones to do tasks by watching.
A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement Learning
Artificial Intelligence
Helps computers understand and use apps like people.
UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning
Machine Learning (CS)
Teaches computers to do many steps on apps.