{
 "id": "skt/TelAgentBench",
 "owner": "skt",
 "name": "TelAgentBench",
 "downloads": 31,
 "likes": 6,
 "last_modified": "2025-11-12T09:49:13.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [],
 "citation": "@inproceedings{lee-etal-2025-telagentbench,\n    title = \"{T}el{A}gent{B}ench: A Multi-faceted Benchmark for Evaluating {LLM}-based Agents in Telecommunications\",\n    author = \"Lee, Sunwoo  and\n      Jang, Daseong  and\n      Arya, Dhammiko  and\n      Han, Gyoung-eun  and\n      Song, Injee  and\n      Kim, SaeRom  and\n      Kim, Sangjin  and\n      Lee, Seojin  and\n      Hong, Seokyoung  and\n      Sek, Sereimony  and\n      Cho, Seung-Mo  and\n      Park, Sohee  and\n      Yoon, Sungbin  and\n      Jang, Wonbeom  and\n      Davis, Eric\",\n    editor = \"Potdar, Saloni  and\n      Rojas-Barahona, Lina  and\n      Montella, Sebastien\",\n    booktitle = \"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track\",\n    month = nov,\n    year = \"2025\",\n    address = \"Suzhou (China)\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.emnlp-industry.83/\",\n    doi = \"10.18653/v1/2025.emnlp-industry.83\",\n    pages = \"1173--1211\",\n    ISBN = \"979-8-89176-333-3\",\n    abstract = \"As Large Language Models (LLMs) evolve into powerful agentic systems, the telecommunications industry{'}s expansion into AI services necessitates industry-grounded benchmarks to evaluate their underexplored domain-specific capabilities. To address the gap left by generic benchmarks that fail to assess realistic, non-English performance, we present TelAgentBench, a Korean benchmark for the telecommunications domain evaluating five co",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "aa966caa3dd2fa2bb0e01983e6f2e5e4153794b4",
 "stated_evidence": "https://huggingface.co/datasets/skt/TelAgentBench/blob/aa966caa3dd2fa2bb0e01983e6f2e5e4153794b4/README.md",
 "file_evidence": "https://huggingface.co/datasets/skt/TelAgentBench/tree/aa966caa3dd2fa2bb0e01983e6f2e5e4153794b4",
 "card_nc": false
}