# WebLINX

Demonstrations and evaluation for conversational web navigation.

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

## Limitations

Inclusion does not establish reproducibility or endorsement.

- Record JSON: https://awesomecua.github.io/resources/github-mcgill-nlp-weblinx/record.json

## Structured profile

- actions: predicted browser actions
- evaluation: Offline evaluation compares action predictions against recorded human demonstrations.
- focus: conversational web navigation, next-action prediction
- observations: dialogue history, HTML, screenshots, action history
- setting: offline

### Count observations

- ≈ 100,000 interactions — original paper benchmark (reported; source: https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50)
- ≈ 2,300 expert demonstrations — original paper benchmark (reported; source: https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50)
- > 150 websites — original paper benchmark (reported; source: https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50)

The figures are rounded descriptions from the original paper. WebLINX 1.1 / BrowserGym removes some demonstrations and changes evaluated steps, including tab actions; do not mix those results or counts with the original release. This profile does not treat replayed demonstration steps as live task completion.

## License declarations

- code: Apache-2.0 — https://raw.githubusercontent.com/mcgill-nlp/weblinx/HEAD/LICENSE
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://raw.githubusercontent.com/mcgill-nlp/weblinx/HEAD/README.md (retrieved 2026-10-16T06:35:57Z; SHA-256 15c3f1656afd861894b180bca7d9214b4cf78a6ad9cd0601c80f5d67d2839528)
- https://raw.githubusercontent.com/mcgill-nlp/weblinx/HEAD/README.md (retrieved 2026-10-16T06:35:57Z; SHA-256 15c3f1656afd861894b180bca7d9214b4cf78a6ad9cd0601c80f5d67d2839528)
- https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50 (retrieved 2026-10-16T06:31:24Z; SHA-256 3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9)
- https://huggingface.co/datasets/McGill-NLP/WebLINX/raw/main/README.md (retrieved 2026-10-17T02:03:23Z; SHA-256 9bd7512e257f5914d66b091530d7eb711a6f90bc21dc89cbba53015c7136c527)
- https://raw.githubusercontent.com/mcgill-nlp/weblinx/HEAD/LICENSE (retrieved 2026-10-16T06:41:57Z; SHA-256 cc0156153933fb96f6f3bf8d736c15e24d78d0838945c2ed456e3ada96cf67c4)