Add WebArena Lite #368
Merged
Add WebArena Lite #368
Conversation
This file contains hidden or 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
recursix
previously approved these changes
Sep 9, 2025
jardinetsouffleton
approved these changes
Sep 10, 2025
|
Hey, doesn't this package need to be added as a dependency to |
Collaborator
Author
It indeed does and will be included before the next release :) . |
layahaasini
pushed a commit
to layahaasini/BrowserGym
that referenced
this pull request
Nov 21, 2025
* Add webarenalite * use old_task_id for webarena lite * include only the lite metadata in webarenalite metadata * Add code acknowledgement * black * update test * remove unused import
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add WebArena Lite from VisualAgentBench
This pull request introduces the new "WebArena Lite" benchmark to the BrowserGym project. It adds a new package (
browsergym/webarenalite) with its own configuration, tasks, and dependencies, and integrates this benchmark into the experiment and environment selection logic. The key changes are grouped below:WebArena Lite Benchmark Integration
browsergym/webarenalite, to the project installation process in theMakefile, ensuring it is installed with other BrowserGym components.browsergym.webarenalitewhen a task name starts with "webarena", ensuring tasks are correctly registered and available.New Package: browsergym/webarenalite
pyproject.toml) and dependencies (requirements.txt) forbrowsergym-webarenalite, specifying its requirements and build configuration. [1] [2]__init__.pyto register all WebArena Lite tasks using task IDs from the new config, and ensured necessary NLTK resources are available at runtime.config.py, providing a central reference for all tasks included in the benchmark.Benchmark Metadata
webarenalite.csv) listing all tasks, their properties, and dependencies for the WebArena Lite benchmark.Description by Korbit AI
What change is being made?
Add WebArena Lite as a new benchmark to the BrowserGym project, including configuration, setup, and evaluation logic for tasks, as well as the necessary dependencies.
Why are these changes being made?
The addition of WebArena Lite expands the benchmarks available within the BrowserGym ecosystem, enabling testing of lightweight tasks that require simpler environments and possibly fewer computational resources. This new benchmark aims to provide broader test coverage and flexibility for benchmarking web-based AI models. The integration includes configuration files, task registration, and evaluation logic tailored for the WebArena Lite environment, mimicking successful patterns from similar benchmark implementations like WebArena and VisualAgentBench.