{"url":"/dataset/kagentbench","name":"KAgentBench","full_name":null,"description_markdown":"KAgentBench is a benchmark dataset of over 3,000 human-edited, automated evaluation data for testing agent capabilities, with evaluation dimensions including planning, tool use, reflection, concluding, and profiling.","description_withheld":null,"homepage":"https://github.com/kwaikeg/kwaiagents","introduced_date":"2023-12-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/kwaiagents-generalized-information-seeking","title":"KwaiAgents: Generalized Information-seeking Agent System with Large Language Models","first_author":"Haojie Pan","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["KAgentBench"],"data_loaders":[],"num_papers_in_archive":1,"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."}