{
 "id": "Rtian/MiRL-train",
 "owner": "Rtian",
 "name": "MiRL-train",
 "downloads": 334,
 "likes": 2,
 "last_modified": "2026-10-27T14:12:45.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{tian2026mirlerrortargetedreinforcementlearning,\n      title={MiRL: Error-Targeted Reinforcement Learning for Correcting Terminal Agent Misbehaviors},\n      author={Runchu Tian and Zaid Khan and Zun Wang and Justin Chih-Yao Chen and Mohit Bansal},\n      year={2026},\n      eprint={2610.35697},\n      archivePrefix={arXiv},\n      primaryClass={cs.LG},\n      url={https://arxiv.org/abs/2610.35697},\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "567907afc96f96fa4d85c99b1cd81ea9862e3979",
 "stated_evidence": "https://huggingface.co/datasets/Rtian/MiRL-train/blob/567907afc96f96fa4d85c99b1cd81ea9862e3979/README.md",
 "file_evidence": "https://huggingface.co/datasets/Rtian/MiRL-train/tree/567907afc96f96fa4d85c99b1cd81ea9862e3979",
 "card_nc": false
}