{
 "id": "wyy1112/Plan-RewardBench",
 "owner": "wyy1112",
 "name": "Plan-RewardBench",
 "downloads": 168,
 "likes": 4,
 "last_modified": "2026-04-18T11:37:35.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "apache-2.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "reinforcement-learning"
 ],
 "citation": "@article{wang2026aligning,\n  title={Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling},\n  author={Wang, Jiaxuan and Hu, Yulan and Yang, Wenjin and Pan, Zheng and Li, Xin and Guo, Lan-Zhe},\n  journal={arXiv preprint arXiv:2604.08178},\n  year={2026}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "d6e9b6a9fc6e5e139a02ecf419cf740a4601d8fc",
 "stated_evidence": "https://huggingface.co/datasets/wyy1112/Plan-RewardBench/blob/d6e9b6a9fc6e5e139a02ecf419cf740a4601d8fc/README.md",
 "file_evidence": "https://huggingface.co/datasets/wyy1112/Plan-RewardBench/blob/d6e9b6a9fc6e5e139a02ecf419cf740a4601d8fc/LICENSE",
 "card_nc": false
}