{"url":"/dataset/androidworld","name":"AndroidWorld","full_name":null,"description_markdown":"AndroidWorld is an environment for building and benchmarking autonomous computer control agents.\r\n\r\nIt runs on a live Android emulator and contains a highly reproducible benchmark of 116 hand-crafted tasks across 20 apps, which are dynamically instantiated with randomly-generated parameters to create millions of unique task variations.\r\n\r\nIn addition to the built-in tasks, AndroidWorld also supports the popular web benchmark, MiniWoB++ from Liu et al..\r\n\r\nKey features of AndroidWorld include:\r\n\r\n📝 116 diverse tasks across 20 real-world apps\r\n🎲 Dynamic task instantiation for millions of unique variations\r\n🏆 Durable reward signals for reliable evaluation\r\n🌐 Open environment with access to millions of Android apps and websites\r\n💾 Lightweight footprint (2 GB memory, 8 GB disk)\r\n🔧 Extensible design to easily add new tasks and benchmarks\r\n🖥️ Integration with MiniWoB++ web-based tasks","description_withheld":null,"homepage":"https://google-research.github.io/android_world/","introduced_date":"2024-05-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/androidworld-a-dynamic-benchmarking","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","first_author":"Christopher Rawles","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["AndroidWorld"],"data_loaders":[],"num_papers_in_archive":27,"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."}