WebArena: A Realistic Web Environment for Building Autonomous Agents

Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzheng Xu, Rundong Li, Bo Li, Tao Chen, Dan Roth, Luke Zettlemoyer

Dataset 2023 Published 2023-07-25 ICLR 2024 arXiv:2307.13854 Indexed 2026-09-06 benchmarkweb-agentevaluation

Abstract

A standalone, self-hostable web environment with realistic websites for evaluating autonomous web agents on long-horizon tasks.

Cite this entry

GB/T 7714-2015

Zhoujun Cheng, Tianbao Xie, Peng Shi, et al. WebArena: A Realistic Web Environment for Building Autonomous Agents[EB/OL]. ICLR 2024, 2023(2023-07-25)[2026-09-16]. https://arxiv.org/abs/2307.13854.

BibTeX

@misc{cheng2023,
  author = {Zhoujun Cheng and Tianbao Xie and Peng Shi and Chengzheng Xu and Rundong Li and Bo Li and Tao Chen and Dan Roth and Luke Zettlemoyer},
  title = {WebArena: A Realistic Web Environment for Building Autonomous Agents},
  year = {2023},
  organization = {ICLR 2024},
  howpublished = {\url{https://arxiv.org/abs/2307.13854}},
}

Visit source ↗

This entry is part of the AgentNet Observer library. Attribute with a link to this page when quoting.