[2603.05044] WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents

Computer Science > Artificial Intelligence arXiv:2603.05044 (cs) [Submitted on 5 Mar 2026] Title:WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents Authors:Sicheng Fan, Qingyun Shi, Shengze Xu, Shengbo Cai, Tieyong Zeng, Li Ling, Yanyi Shang, Dehan Kong View a PDF of the paper titled WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents, by Sicheng Fan and 7 other authors View PDF HTML (experimental) Abstract:Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or costly, scarce human-crafted data and environments. We argue this focus on data volume overlooks a more critical factor: the efficiency of compressing a large language model's (LLM) latent knowledge into actionable agent behavior. We introduce WebFactory, a novel, fully automated closed-loop reinforcement learning pipeline for GUI agents, systematically compressing LLM-encoded internet intelligence into efficient, grounded actions. Our pipeline features a process of scalable environment synthesis, knowledge-aware task generation, LLM-powered trajectory collection, decomposed reward RL training, and systematic agent evaluation. Remarkably, our agent demonstrates exceptional data efficiency and generalization. Trained on synthetic data from only 10 websites within WebFactory, it achieves performance comparable to GUI agents trained on the same...