{"url":"/dataset/toole","name":"ToolE","full_name":null,"description_markdown":"The ToolE dataset encompasses various types of user queries in the form of prompts. These prompts trigger LLMs to utilize tools, including both single-tool and multi-tool scenarios. The dataset serves as a valuable resource for assessing LLMs’ understanding of tool functionality and their ability to select appropriate tools for specific tasks.","description_withheld":null,"homepage":"https://github.com/HowieHwong/MetaTool","introduced_date":"2023-10-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/metatool-benchmark-deciding-whether-to-use","title":"MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use","first_author":"Yue Huang","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["ToolE"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}