打造可验证、高并发的移动端GUI智能体仿真平台，支持高效强化学习训练。
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
- 用结构化JSON管理状态，实现确定性评判与低成本并行推演。
- 单服务器支持数百实例，每实例内存约400MB，冷启动仅需3秒。
- 内置416个参数化任务模板，适合研究移动端AI代理的泛化能力。
我们提出MobileGym，一个基于浏览器的轻量级、完全可控的日常移动端使用环境，旨在保证交互保真度的同时不复现专有后端。该平台实现了以往日常应用难以企及的两大能力：通过基于状态的结构化JSON判定实现可验证的结果信号，以及通过低开销并行采样实现可扩展的在线强化学习。完整环境状态以结构化JSON形式捕获、配置、分叉和比对；单个服务器可承载数百个并行实例，每个实例约400MB内存，冷启动时间约3秒。分层状态模型与声明式任务定义框架确保了大规模下的状态可编程性和任务创建可行性；统一的程序化评判机制同时提供确定性评估结果与密集型强化学习奖励。配套的MobileGym-Bench包含416个参数化任务模板（256个测试+160个训练），覆盖28个应用，具备确定性裁判和结构化AnswerSheet协议，避免自由文本匹配失败。在一次从仿真到真实设备的案例研究中，基于Qwen3-VL-4B-Instruct的GRPO算法在256个任务测试集上提升12.8个百分点；在59个真实设备信号子集上，真实执行保留了仿真训练收益的95.1%。
原文摘要 · Abstract (English)
We present MobileGym, a browser-hosted, lightweight, fully controllable environment for everyday mobile use, targeting interaction fidelity without replicating proprietary backends. It enables two capabilities previously out of reach for everyday apps: verifiable outcome signals through deterministic state-based judging over structured JSON state, and scalable online RL through low-cost parallel rollouts. The full environment state is captured, configured, forked, and compared as structured JSON, and a single server can host hundreds of parallel instances, with about 400 MB memory per instance and about 3 s cold start. A layered state model and a declarative task-definition framework keep state programmability and task creation practical at scale, and a single programmatic judging mechanism delivers both deterministic evaluation verdicts and dense RL rewards. The accompanying MobileGym-Bench provides 416 parameterized task templates, including 256 test and 160 train templates, over 28 apps, with deterministic judges and a structured AnswerSheet protocol that avoids free-text matching failures. In a Sim-to-Real case study, GRPO on Qwen3-VL-4B-Instruct gains +12.8 percentage points on the 256-task test set, and on a 59-task real-device signal subset, real-device execution retains 95.1% of the simulation-side training gain. Project page: https://mobilegym.github.io.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。