# WebVoyager

Multimodal web navigation agent and evaluation tasks on real websites.

- Catalog URL: https://awesomecua.github.io/resources/github-minorjerry-webvoyager/
- Original source: https://github.com/MinorJerry/WebVoyager
- Kind: benchmark
- Review: curated
- Scope: core
- Environments: web
- Topics: evaluation, web-navigation
- Evidence checked: 2026-10-16T06:35:57Z
- ID: github:minorjerry/webvoyager

## Limitations

Inclusion does not establish reproducibility or endorsement.

- Record JSON: https://awesomecua.github.io/resources/github-minorjerry-webvoyager/record.json

## Structured profile

- actions: Selenium-backed browser interactions
- evaluation: The repository supplies an automated multimodal-model evaluation protocol.
- focus: live-web task completion
- observations: webpage screenshots, textual task instructions
- setting: interactive

### Count observations

- 643 task queries — WebVoyager task collection (reported; source: https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/README.md)
- 15 websites — WebVoyager task collection (reported; source: https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/README.md)
- 90 tasks — separate GAIA validation-derived web subset (reported; source: https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/README.md)

The GAIA-derived subset is separate from the 643 WebVoyager queries. Live sites and time-sensitive travel tasks can change; record the task snapshot and evaluation date.

## License declarations

- code: Apache-2.0 — https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/LICENSE
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/README.md (retrieved 2026-10-16T06:35:57Z; SHA-256 b5523941b2773634fdcf359b5b89bf0aca589f33ad9db30692c8b1912ed5dda5)
- https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/LICENSE (retrieved 2026-10-16T06:41:57Z; SHA-256 43070e2d4e532684de521b885f385d0841030efa2b1a20bafb76133a5e1379c1)
