WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

arXiv:2401.13919v3 Announce Type: replace
Abstract: The rapid advancement of large language models (LLMs) has led to a new era marked by the development of autonomous applications in real-world scenarios, which drives innovation in creating advanced web agents. Existing web agents typically only handle one input modality and are evaluated only in simplified web simulators or static web snapshots, greatly limiting their applicability in real-world scenarios. To bridge this gap, we introduce WebVoyager, an innovative Large Multimodal Model (LMM) powered web …

abstract advanced advancement agent agents applications arxiv autonomous building cs.ai cs.cl development innovation language language models large language large language models large multimodal models llms multimodal multimodal models type web world