WebHarbor 提供 153 個可演進網站環境,支援 GUI 智能體評測與訓練
WebHarbor: Docking Real Websites for Evolving GUI Agent Environments
WebHarbor 提供 153 個可執行、以 Docker 容器化的網站環境,用於穩定評測 GUI 智能體及進行強化學習訓練。這些環境在確定性控制下重建真實網上服務的介面、內容和功能流程,涵蓋 3,518 項任務,包括多步驟及登入後流程。
Published on Nov 2
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
WebHarbor provides 153 executable, dockerized web environments for stable evaluation and reinforcement learning training of GUI agents, enabling strong generalization across multi-step and post-authentication tasks.
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.
View arXiv page View PDF Project page GitHub Add to collection
Models citing this paper 1
Image-Text-to-Text • 5B • Updated about 15 hours ago • 39ChilleD/WebHarbor-4B
Datasets citing this paper 2
ChilleD/WebHarbor
Updated about 15 hours ago • 8.73k • 2
ChilleD/WebHarbor-Tasks
Updated about 15 hours ago • 607
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.03634 in a Space README.md to link it from this page.
Collections including this paper 1
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co