{
 "id": "GloriaGeng/REALM-Bench",
 "owner": "GloriaGeng",
 "name": "REALM-Bench",
 "downloads": 139,
 "likes": 1,
 "last_modified": "2026-05-21T22:03:51.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "other"
 ],
 "citation": "@misc{geng2025realmbenchbenchmarkevaluatingmultiagent,\n  title={REALM-Bench: A Benchmark for Evaluating Multi-Agent Systems on Real-world, Dynamic Planning and Scheduling Tasks},\n  author={Longling Geng and Edward Y. Chang},\n  year={2025},\n  eprint={2502.18836},\n  archivePrefix={arXiv},\n  primaryClass={cs.AI},\n  url={https://arxiv.org/abs/2502.18836},\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "aefdc398b21567d264f9eb9e27920483b376355d",
 "stated_evidence": "https://huggingface.co/datasets/GloriaGeng/REALM-Bench/blob/aefdc398b21567d264f9eb9e27920483b376355d/README.md",
 "file_evidence": "https://huggingface.co/datasets/GloriaGeng/REALM-Bench/tree/aefdc398b21567d264f9eb9e27920483b376355d",
 "card_nc": false
}