{
  "aliases": [],
  "authors": [],
  "details": {},
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T02:02:06Z",
      "role": "primary",
      "sha256": "eb217b96c54c3c2ccfd3a27255c6fd740df40c2d6743ae811858339bf7f740b0",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations"
      ],
      "url": "https://raw.githubusercontent.com/THUDM/WebRL/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T02:02:05Z",
      "role": "primary",
      "sha256": "42496cf0cff06a7f9e794f4313a10a670bc48df9909ec6d57763cb902bb229ea",
      "supports": [
        "identity"
      ],
      "url": "https://api.github.com/repos/THUDM/WebRL"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T02:02:05Z",
      "role": "primary",
      "sha256": "bb1683c6fb5ff658c89f0ebf0f8baf8026bb703840e174c9e46b223c85a16856",
      "supports": [
        "release_status"
      ],
      "url": "https://api.github.com/repos/THUDM/WebRL/git/trees/main?recursive=1"
    }
  ],
  "id": "github:thudm/webrl",
  "identifiers": {},
  "kind": "framework",
  "last_verified_at": "2026-10-17T02:02:06Z",
  "licenses": {
    "code": null,
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/THUDM/WebRL"
    }
  ],
  "name": "WebRL",
  "notes": "Training code and checkpoint links are released. No root code-license declaration was found in the inspected repository metadata; bundled dependency licenses do not establish a license for the whole project. Weights have separate Hub terms.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/THUDM/WebRL/HEAD/README.md",
      "target_id": "arxiv:2411.02337",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Training pipeline that evolves web tasks from prior attempts and uses an outcome reward model to refine browser policies.",
  "topics": [
    "reinforcement-learning",
    "web-navigation",
    "data-generation"
  ],
  "updated_at": null,
  "url": "https://github.com/THUDM/WebRL"
}