{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "Selenium-backed browser interactions"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/README.md",
          "population": "WebVoyager task collection",
          "qualifier": "exact",
          "unit": "task queries",
          "value": 643
        },
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/README.md",
          "population": "WebVoyager task collection",
          "qualifier": "exact",
          "unit": "websites",
          "value": 15
        },
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/README.md",
          "population": "separate GAIA validation-derived web subset",
          "qualifier": "exact",
          "unit": "tasks",
          "value": 90
        }
      ],
      "evaluation": "The repository supplies an automated multimodal-model evaluation protocol.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/README.md"
      ],
      "focus": [
        "live-web task completion"
      ],
      "notes": "The GAIA-derived subset is separate from the 643 WebVoyager queries. Live sites and time-sensitive travel tasks can change; record the task snapshot and evaluation date.",
      "observations": [
        "webpage screenshots",
        "textual task instructions"
      ],
      "setting": "interactive"
    }
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:57Z",
      "role": "primary",
      "sha256": "b5523941b2773634fdcf359b5b89bf0aca589f33ad9db30692c8b1912ed5dda5",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details.benchmark_protocol"
      ],
      "url": "https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/README.md"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-16T06:41:57Z",
      "role": "primary",
      "sha256": "43070e2d4e532684de521b885f385d0841030efa2b1a20bafb76133a5e1379c1",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/LICENSE"
    }
  ],
  "id": "github:minorjerry/webvoyager",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T06:35:57Z",
  "licenses": {
    "code": {
      "basis": "repository LICENSE header; not a weights/data license",
      "declared": "Apache-2.0",
      "retrieved_at": "2026-10-16T06:41:57Z",
      "url": "https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/MinorJerry/WebVoyager"
    }
  ],
  "name": "WebVoyager",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/MinorJerry/WebVoyager/HEAD/README.md",
      "target_id": "arxiv:2401.13919",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Multimodal web navigation agent and evaluation tasks on real websites.",
  "topics": [
    "evaluation",
    "web-navigation"
  ],
  "updated_at": null,
  "url": "https://github.com/MinorJerry/WebVoyager"
}