You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
> This repository hosts the *canonical* implementation of WebArena to reproduce the results reported in the paper. The web navigation infrastructure has been significantly enhanced by [AgentLab](https://github.com/ServiceNow/AgentLab/), introducing several key features: (1) support for parallel experiments using [BrowserGym](https://github.com/ServiceNow/BrowserGym), (2) integration of popular web navigation benchmarks (e.g., VisualWebArena) within a unified framework, (3) unified leaderboard reporting, and (4) improved handling of environment edge cases. We strongly recommend using this framework for your experiments.
## News
*[12/20/2024] Check out our new benchmark on even more consequential tasks, including terminal use and coding, [TheAgentCompany]([./resources/README.md#12212023-human-trajectories](https://the-agent-company.com/)).
*[12/21/2023] We release the recording of trajectories performed by human annotators on ~170 tasks. Check out the [resource page](./resources/README.md#12212023-human-trajectories) for more details.
