OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents 文章

ArXiv CS.CV2026-06-05NEWSen作者: Rui Yang, Qianhui Wu, Yuxi Chen, Hao Bai, Wenlin Yao, Hao Cheng, Baolin Peng, Huan Zhang, Tong Zhang, Jianfeng Gao

摘要

arXiv:2606.02031v2 Announce Type: replace-cross Abstract: Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the strongest systems remain largely proprietary, while open agents still depend heavily on supervised post-training over large collections of curated web trajectories. This dependence creates a major scalability bottleneck: high-quality demonstrations are expensive to collect, and static datasets offer limited coverage of the diverse, ever-changing open web. Although online RL has shown promise for text-based agents, its potential for training visual web agents directly on live websites remains largely underexplored. In this paper, we introduce OpenWebRL, an open framework for training visual web agents with online multi-turn RL on real websites.

相关公司

暂无数据

相关人物

暂无数据

相关技术查看全部 (1)