OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
2026-06-01 • Machine Learning
Machine LearningArtificial IntelligenceComputation and LanguageComputer Vision and Pattern Recognition
AI summaryⓘ
The authors created OpenWebRL, an open system that trains visual web agents to better understand and interact with live websites using online reinforcement learning (RL). Their approach avoids the need for many expensive, pre-collected training examples by learning directly from real-time website interactions. They show that their agent, OpenWebRL-4B, performs well on tough web tasks, even competing with some private systems. The authors also explore what makes online RL work well for these agents and share their data and code to help others build on their work.
visual web agentsreinforcement learningonline RLmulti-turn interactionweb automationpolicy optimizationtrajectory success judginglive-browser infrastructureopen-sourcebenchmark evaluation
Authors
Rui Yang, Qianhui Wu, Yuxi Chen, Hao Bai, Wenlin Yao, Hao Cheng, Baolin Peng, Huan Zhang, Tong Zhang, Jianfeng Gao
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. OpenWebRL covers the full training pipeline, including scalable live-browser infrastructure, supervised initialization, multimodal context management, trajectory-level success judging, and efficient multi-turn policy optimization. Using this framework, we train OpenWebRL-4B, which establishes a new open-source state of the art on challenging live-web benchmarks. With only 0.4K initialization trajectories and 2.2K open-ended RL training tasks, OpenWebRL-4B achieves 67.0% success on Online-Mind2Web and 64.0% on DeepShop, outperforming prior open agents of similar or larger scale and remaining competitive with proprietary systems including OpenAI CUA and Gemini CUA. Beyond strong benchmark performance, we systematically study the key design choices that make online RL effective for visual web agents, and analyze how RL improves agentic reasoning. Overall, our work offers a practical path toward building more capable, reproducible, and cost-efficient open web agents. We will release our training data, models, and code to support future research.