AI 学用网站，终于有了不会变脸的考场
训练 AI 操作网页，最大的麻烦是网站会变：今天能点的按钮明天就改版，登录后的流程又常常被挡在墙外。WebHarbor 把 153 个真实网站「装进罐头」——界面、内容、操作流程都原样复刻，但完全由你控制，不会突然变。更关键的是，它靠「人机协作」来造：AI 负责按新任务扩展功能，人负责检查像不像、对不对，最终攒出 3518 个任务，覆盖多步骤和登录后的复杂操作。用这套环境训练一个 40 亿参数的小模型，它就能在没见过的任务上表现接近顶尖开源模型。这不是你明天能用的工具，但它解决了 AI 学用网站时「考场总在变」的根本问题。
📄 原文摘要(英文)
GUI web agents require realistic and interactive environments that remain stable during both evaluation and training. Live website evaluation suffers from changing content, access restrictions, and limited coverage of authenticated workflows, while existing synthetic environments for training often lack functional depth and visual fidelity. We propose WebHarbor, a suite of 153 executable and dockerized website environments that faithfully reconstruct the visual interfaces, content, and functional workflows of real-world web services under deterministic control. We build WebHarbor through task-driven human-agent collaboration, where environments evolve as new tasks expand their functional scope, coding agents implement the required changes, and human contributors audit visual fidelity, functional correctness, and task validity. The resulting suite comprises 3,518 tasks spanning multi-step and post-authentication workflows, where existing works often fail to cover. Beyond reliable evaluation, WebHarbor provides high-fidelity synthetic web environments for cost-efficient reinforcement learning (RL). We demonstrate that a Qwen 4B-level GUI agent trained with RL in WebHarbor generalizes to unseen tasks and performs competitively with leading open-source GUI web agents across four benchmarks. The code and data are publicly available at https://github.com/aiming-lab/WebHarbor.