Running 7 7 Online-Mind2Web Leaderboard 🏆 Display and visualize evaluation results for human and automated agents
SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills Paper • 2504.07079 • Published 14 days ago • 11
An Illusion of Progress? Assessing the Current State of Web Agents Paper • 2504.01382 • Published 22 days ago • 1
Mind2Web Collection Towards Generalist Agents for the Web (NeurIPS'23 Spotlight) • 7 items • Updated 14 days ago
WebDreamer Collection Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents • 6 items • Updated 9 days ago • 4