Websites · PROJECT NOTES
WebChoreArena
A distinct task suite built on WebArena's websites, emphasizing tedious workflows that require retaining many details, performing calculations and tracking information across pages.
What can you do with it?
Measure web-agent performance on demanding information-heavy chores using the released task configurations and evaluators.
What should you know before using it?
Adds tasks rather than a new set of websites. Requires separately deployed WebArena services and controlled resets, including before cross-site evaluation. Model/API configuration affects comparisons. Repository code is Apache 2.0; upstream components retain their own terms.
What is verified here?
This entry was reviewed against original project material. We have not independently run the software or reproduced its results. AI-development claims are author-reported; check upstream for current versions, setup requirements, and licenses.
- Resource type
- Benchmark suite
- Provenance
- Development provenance not established
- Reviewed
- Platforms
- Web