运行世界模型（Operational World Models, OWMs）需要与物理世界进行结构化交互：它们必须观测运行状态、施加受控动作、测量后果、保存经验，并利用这些经验支持预测和预防性决策。本文介绍了 AutoLab，这是一个互联网可访问的实验平台，为无线网络的 OWMs 提供上述物理基础功能。远程研究人员可以检查实时测试站点，重建近期状态历史，编写包含机器人、接入点、无线扫描和流量操作的时间序列实验，在本地验证后提交相同的显式契约进行注册。在物理站点，集中式网络管理系统（NMS）重新验证并调度实验，协调分布式设备代理，从原始相机观测中估计机器人位置，监督物理执行，并记录测量数据和诊断状态。在编写和注册边界使用相同的 Python 验证规则，而目标级命令将互联网用户与底层设备控制隔离。端到端移动性轨迹演示了 NMS 如何检测大的物理运动误差，发出纠正动作，并在不向脚本编写者或机器人代理暴露该误差的情况下恢复预期的实验轨迹。因此，AutoLab 贡献了一种可复现的互联网到物理实验及反馈基础设施，而非声称已完成自主 OWM。其结构化的时空记录为生成场景、预测风险评估和预防性无线网络管理的后续工作提供了所需的经验。

Operational World Models (OWMs) require structured interaction with the physical world: they must observe operational state, impose controlled actions, measure consequences, preserve experience, and use that experience to support prediction and preventive decision making. This paper presents Autolab, an Internet-accessible experimental platform that provides these physical grounding functions for wireless-network OWMs. A remote researcher can inspect a live test site, reconstruct recent state history, author a time-ordered experiment containing robot, access-point, wireless-scan, and traffic operations, validate it locally, and submit the same explicit contract for registration. At the physical site, a centralized network management system (NMS) revalidates and schedules the experiment, coordinates distributed device agents, estimates robot location from raw camera observations, supervises physical execution, and records measurements and diagnostic state. The same Python validation rules are used at the authoring and registration boundaries, while destination-level commands isolate Internet users from low-level device control. An end-to-end mobility trace demonstrates how the NMS detects a large physical movement error, issues corrective motion, and restores the intended experiment trajectory without exposing that error to the script writer or robot agent. Autolab therefore contributes a reproducible Internet-to-physical experimentation and feedback infrastructure, rather than claiming a completed autonomous OWM. Its structured spatial--temporal records provide the experience needed for continuing work on generative scenarios, predictive risk evaluation, and preventive wireless-network management.