Web-Shepherd inference and evaluation
Process-reward inference and benchmark-evaluation utilities that use task checklists to assess individual web-agent decisions.
AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.
What is this resource?
- Resource type
- Tools
- Environment
- web
- Topics
- reward-models, evaluation, web-navigation
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-17T02:44:04Z
- Resource ID
- github:kyle8581/web-shepherd
What licenses are recorded?
Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.
- Code
- Not recorded
- Data
- Not recorded
- Document
- Not recorded
- Weights
- Not recorded
Explore related topics
Scope and 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.
Primary evidence and verification
Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.
- editorial primary review
Retrieved 2026-10-17T02:44:04Z. Supports: name, kind, summary, environments, topics, scope, relations.
Content fingerprint
07431058d8b9a71b80e75b7a74a40a8346c1503eec240628459cc4d4e2f0802f - editorial primary review
Retrieved 2026-10-17T02:44:04Z. Supports: identity.
Content fingerprint
52925efd66489696c4e1f31f0f8353997fe534df9fcd42e50232cc78f0506903 - editorial primary review
Retrieved 2026-10-17T02:44:04Z. Supports: release_status.
Content fingerprint
ba7d28866cec4fb889499fc011473aedcdcc36fd8175c73527eafd7ef6b6dbba
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.