# Web-Shepherd inference and evaluation

Process-reward inference and benchmark-evaluation utilities that use task checklists to assess individual web-agent decisions.

- Catalog URL: https://awesomecua.github.io/resources/github-kyle8581-web-shepherd/
- Original source: https://github.com/kyle8581/Web-Shepherd
- Kind: tool
- Review: curated
- Scope: core
- Environments: web
- Topics: reward-models, evaluation, web-navigation
- Evidence checked: 2026-10-17T02:44:04Z
- ID: github:kyle8581/web-shepherd

## Limitations

The tree contains src/webprm modules and a WebRewardBench evaluation script. The README’s illustrative folder layout differs from the actual tree, so a complete training pipeline is not claimed. No root code license is declared. Some old checkpoint links are unavailable; current model releases are separately identified through the official Hub collection.

- Record JSON: https://awesomecua.github.io/resources/github-kyle8581-web-shepherd/record.json

## License declarations

- code: not recorded
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://raw.githubusercontent.com/kyle8581/Web-Shepherd/HEAD/README.md (retrieved 2026-10-17T02:44:04Z; SHA-256 07431058d8b9a71b80e75b7a74a40a8346c1503eec240628459cc4d4e2f0802f)
- https://api.github.com/repos/kyle8581/Web-Shepherd (retrieved 2026-10-17T02:44:04Z; SHA-256 52925efd66489696c4e1f31f0f8353997fe534df9fcd42e50232cc78f0506903)
- https://api.github.com/repos/kyle8581/Web-Shepherd/git/trees/main?recursive=1 (retrieved 2026-10-17T02:44:04Z; SHA-256 ba7d28866cec4fb889499fc011473aedcdcc36fd8175c73527eafd7ef6b6dbba)