{
  "id": "test-set:tau-bench-airline-retail",
  "_kind": "TestSet",
  "_file": "benchmarks/test-sets/source-backed-benchmark-test-sets.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "displayName": "tau-bench airline and retail domains",
    "benchmarkId": "benchmark:tau-bench",
    "releasedAt": "2024-06-17",
    "composition": "Original tau-bench customer-service domains for tool-agent-user\ninteractions in airline and retail settings, with simulated users,\npolicy constraints, and domain APIs.\n",
    "homepageUrl": "https://openreview.net/forum?id=roNSXZpUDN",
    "description": "Source-backed tau-bench domain artifact for multi-turn tool-use and\npolicy-following evaluation.\n"
  },
  "outgoingEdges": [
    {
      "from": "test-set:tau-bench-airline-retail",
      "to": "benchmark:tau-bench",
      "kind": "belongs_to_benchmark"
    }
  ],
  "incomingEdges": []
}