Research2026-05-01
OpAgent: Operator Agent for Web Navigation
Source: Arxiv CS.AI
arXiv:2602.13559v2 Announce Type: replace Abstract: To fulfill user instructions, autonomous web agents must contend with the inherent complexity and volatile nature of real-world websites. Conventional paradigms predominantly rely on Supervised Fine-Tuning (SFT) or Offline Reinforcement Learning...
arxivpapersagents