AI RESEARCH
Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration
arXiv CS.AI
•
ArXi:2605.31365v1 Announce Type: new Recent advances in Multimodal Large Language Models (MLLMs) have led to promising progress in web agents. However, existing web agents often rely on handcrafted execution pipelines or expensive expert trajectories, limiting their adaptability to complex, dynamic environments.