Models and checkpoints

WebRL Llama 3.1 8B

A WebRL browser-policy checkpoint for performing actions in the five website environments of WebArena.

AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.

Original source ↗Read as Markdown Record JSON

What is this resource?

Resource type: Models and checkpoints
Environment: web
Topics: web-navigation, reinforcement-learning
Record publication date: Not recorded
Evidence retrieved: 2026-10-17T02:05:40Z
Resource ID: url:a6ee20fea67438d91e06

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: other (publisher model/dataset card metadata; third-party assets retain their own terms)

Recorded specifications

disabled: false
download url: https://huggingface.co/zai-org/webrl-llama-3.1-8b/tree/main
gated: false
hub id: zai-org/webrl-llama-3.1-8b

Explore related topics

Web navigation Reinforcement learning

Scope and limitations

The official Hub API resolves the former THUDM namespace to zai-org. Seven safetensors shards and configuration/tokenizer files are public and ungated. The card marks the weight license as other without naming complete terms, so no permissive weight license is inferred. The card’s evaluation prose also names GLM-4 despite the Llama checkpoint identity; no score is imported.

Related resources

documented by: WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

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 2026-10-17T02:05:40Z. Supports: name, kind, summary, environments, topics, scope, relations, details.
Content fingerprint
4712446382f106a115a317d0ec6273a975545386b9cedf56946a96a56479dc9f
editorial primary review
Retrieved 2026-10-17T02:05:40Z. Supports: identity, release_status, details, licenses.weights.
Content fingerprint
6523b7f198d8debec2f3074190812955c6251590b61f8a6ea1bbb681b8ea128f
editorial primary review
Retrieved 2026-10-17T02:02:28Z. Supports: identity.
Content fingerprint
6523b7f198d8debec2f3074190812955c6251590b61f8a6ea1bbb681b8ea128f
huggingface card
Retrieved 2026-10-17T02:05:40Z. Supports: licenses.weights.
Content fingerprint
4712446382f106a115a317d0ec6273a975545386b9cedf56946a96a56479dc9f
huggingface repository identity
Retrieved 2026-10-17T19:15:06Z. Supports: aliases.
Content fingerprint
96621f060dddec91453d8c2b451b3793a34b34810d82c7cd13ce4cb05ca90a76
huggingface repository identity
Retrieved 2026-10-17T19:15:06Z. Supports: aliases.
Content fingerprint
96621f060dddec91453d8c2b451b3793a34b34810d82c7cd13ce4cb05ca90a76

Suggest a correction

Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.