Builder

web-arena-x

1 Tool

web-arena-x is the GitHub organization behind WebArena, a research benchmark created by a team at Carnegie Mellon University, including Shuyan Zhou, Frank F. Xu, and Graham Neubig, for evaluating autonomous web agents on realistic, long-horizon browsing tasks. The organization also maintains VisualWebArena and related extensions for multimodal and verified agent benchmarking.