# Generalization in Online Reinforcement Learning for Mobile Agents Source: [Generalization in Online Reinforcement Learning for Mobile Agents]() Collection index: [llms.txt]() Data updated: 2026-03-11T05:00:04.182Z Authors: Li Gu, Zihuan Jiang, Zhixiang Chi, Huan Liu, Ziqiang Wang, Yuanhao Yu, Glen Berseth, Yang Wang Published: 2026-03-08T03:08:11.000Z ## Abstract Graphical user interface (GUI)-based mobile agents automate digital tasks on mobile devices by interpreting natural-language instructions and interacting with the screen. While recent methods apply reinforcement learning (RL) to train vision-language-model(VLM) agents in interactive environments with a primary focus on performance, generalization remains underexplored due to the lack of standardized benchmarks and open-source RL systems. In this work, we formalize the problem as a Contextual Markov Decision Process (CMDP) and introduce \\textbf{AndroidWorld-Generalization}, a benchmark with three increasingly challenging regimes for evaluating zero-shot generalization to unseen task instances, templates, and applications. We further propose an RL training system that integrates Group Relative Policy Optimization (GRPO) with a scalable rollout collection system, consisting of containerized infrastructure and asynchronous execution % , and error recovery to support reliable and efficient training. Experiments on AndroidWorld-Generalization show that RL enables a 7B-parameter VLM agent to surpass supervised fine-tuning baselines, yielding a 26.1\\% improvement on unseen instances but only limited gains on unseen templates (15.7\\%) and apps (8.3\\%), underscoring the challenges of generalization. As a preliminary step, we demonstrate that few-shot adaptation at test-time improves performance on unseen apps, motivating future research in this direction. To support reproducibility and fair comparison, we open-source the full RL training system, including the environment, task suite, models, prompt configurations, and the underlying infrastructure \\footnote{https://github.com/zihuanjiang/AndroidWorld-Generalization}. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Mobile Agent Decision-making on AndroidWorld (Evaluation set 116 templates)](): Mobile Agent Decision-making; AndroidWorld (Evaluation set 116 templates); Average Success Rate (SR): 49.1. ## Original sources and implementation [Original paper]() [PDF]()