WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
#WebFactory #language models #automated compression #web agents #AI deployment #computational efficiency #grounded intelligence
📌 Key Takeaways
- WebFactory automates the compression of foundational language models into efficient web agents.
- The system focuses on grounding language intelligence for practical web-based tasks.
- Automated compression reduces computational overhead while maintaining performance.
- The approach enables scalable deployment of AI agents for web interactions.
📖 Full Retelling
arXiv:2603.05044v1 Announce Type: new
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 le
🏷️ Themes
AI Automation, Web Agents
Entity Intersection Graph
No entity connections available yet for this article.
Original Source
--> Computer Science > Artificial Intelligence arXiv:2603.05044 [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 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 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 amount of human-annotated data from a much larger set of environments. This superior performance is consistent across our internal offline and online transfer benchmarks, where our agent also significantly outperforms the base foundation model. We further provide critical insights into the "embodiment potential" of different LLM foundations, offering a new axis for model evaluation. This work presents a scalable and cost-effective paradigm for transforming passive internet knowledge into active, grounded inte...
Read full article at source