AI RESEARCH
From Imitation to Discrimination: Progressive Curriculum Learning for Robust Web Navigation
arXiv CS.LG
•
ArXi:2604.12666v1 Announce Type: new Text-based web agents offer computational efficiency for autonomous web navigation, yet developing robust agents remains challenging due to the noisy and heterogeneous nature of real-world HTML. Standard Supervised Fine-Tuning (SFT) approaches fail in two critical dimensions: they lack discrimination capabilities to reject plausible but incorrect elements in densely populated pages, and exhibit limited generalization to unseen website layouts. To address these challenges, we.