From 13364716bf3824406392b4d5d661a20ea54982f3 Mon Sep 17 00:00:00 2001 From: Shuyan Zhou Date: Thu, 5 Dec 2024 00:31:16 -0500 Subject: [PATCH] Note on AgentLab --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index b201071..de105c4 100644 --- a/README.md +++ b/README.md @@ -22,6 +22,9 @@ ![Overview](media/overview.png) +## Update on 12/5/2024 +> [!IMPORTANT] +> This repository host 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 * [12/21/2023] 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.