WebShepherd 3B
A public text-based process-reward checkpoint from the Web-Shepherd collection for scoring web-agent decisions against task checklists.
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
- Models and checkpoints
- Environment
- web
- Topics
- reward-models, web-navigation
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-17T02:45:20Z
- Resource ID
- url:72f7fe0211c6551b945f
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
Recorded specifications
- disabled
- false
- download url
- https://huggingface.co/LangAGI-Lab/WebShepherd_3B/tree/main
- gated
- false
- hub id
- LangAGI-Lab/WebShepherd_3B
Explore related topics
Scope and limitations
The official project-linked collection identifies this public 3B checkpoint. The README uses a separate unavailable WebShepherd/web-shepherd-base URL; redirect equivalence is not asserted. Two safetensors shards and a Qwen2 causal-language-model configuration are present. No model card or weight license is published in the inspected manifest. The separately announced multimodal 3B model is not assumed released.
Related resources
- documented by: Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
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 2026-10-17T02:45:20Z. Supports: name, kind, summary, environments, topics, scope, relations, details.
Content fingerprint
6f28e86a99b286a575c5e7f8d24d6901655971e9a091493950b59948f4b9ad9b - editorial primary review
Retrieved 2026-10-17T02:45:05Z. Supports: identity, summary, relations.
Content fingerprint
647d9e7bdad5fe2c03a8cfcd34d93f3b2bf7c1553b517a4a843bc0113fa47456 - editorial primary review
Retrieved 2026-10-17T02:44:04Z. Supports: summary, environments.
Content fingerprint
07431058d8b9a71b80e75b7a74a40a8346c1503eec240628459cc4d4e2f0802f - editorial primary review
Retrieved 2026-10-17T02:49:45Z. Supports: details.
Content fingerprint
252ed290ec84ffd8fa686fb72df68afe7bbd8c19b80538c0b318db60cd107d09 - huggingface api
Retrieved 2026-10-17T02:45:20Z. Supports: details, licenses.weights.
Content fingerprint
6f28e86a99b286a575c5e7f8d24d6901655971e9a091493950b59948f4b9ad9b
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.