{"slug": "webharbor-docking-real-websites-for-evolving-gui-agent-environments", "title": "WebHarbor: Docking Real Websites for Evolving GUI Agent Environments", "summary": "Researchers submitted WebHarbor to arXiv on 2 Nov 2026, a suite of 153 executable, dockerized website environments that reconstruct real web services' interfaces, content and workflows under deterministic control for training and evaluating GUI web agents. WebHarbor spans 3,518 tasks, including multi-step and post-authentication workflows, and a Qwen 4B-level GUI agent trained with reinforcement learning in the suite generalized to unseen tasks and performed competitively with leading open-source GUI web agents across four benchmarks. The code and data are publicly available on GitHub at aiming-lab/WebHarbor.", "body_md": "# Computer Science > Artificial Intelligence\n\n  [Submitted on 2 Nov 2026]\n\n# Title:WebHarbor: Docking Real Websites for Evolving GUI Agent Environments\n\n[View PDF](http://arxiv.org/pdf/2611.03634v1)\n\nAbstract: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 [this https URL](https://github.com/aiming-lab/WebHarbor).\n    \n\n### Additional Features\n\n### Current browse context:\n\ncs.AI\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/webharbor-docking-real-websites-for-evolving-gui-agent-environments", "canonical_source": "http://arxiv.org/abs/2611.03634v1", "published_at": "2026-11-03 15:24:38+00:00", "updated_at": "2026-11-03 15:55:09.711205+00:00", "lang": "en", "topics": ["ai-agents", "ai-research", "artificial-intelligence", "machine-learning"], "entities": ["WebHarbor", "arXiv", "Qwen", "aiming-lab", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/webharbor-docking-real-websites-for-evolving-gui-agent-environments", "markdown": "https://wpnews.pro/news/webharbor-docking-real-websites-for-evolving-gui-agent-environments.md", "text": "https://wpnews.pro/news/webharbor-docking-real-websites-for-evolving-gui-agent-environments.txt", "jsonld": "https://wpnews.pro/news/webharbor-docking-real-websites-for-evolving-gui-agent-environments.jsonld"}}