cua
Datasets
All datasets matching “cua”cuadlite.cuaworld-assets
lite.cuaworld materials
Maintained environment materials for cua-lite's lite.cuaworld.* software
environments — forked from cmu-l3/gym-anything
(CUA-World, MIT) and curated/edited/expanded by us. Published as the Hugging Face dataset
cua-lite/lite.cuaworld-assets.
This repo holds content only (no engine code): per-environment env.json,
install/setup scripts/, per-task assets (tasks/<task>/…), data/, config/,
assets/, optional post_build.sh, and a curated registered.json. The… See the full description on the dataset page: https://huggingface.co/datasets/cua-lite/lite.cuaworld-assets.Lite.ScaleCUA
cua-lite/Lite.ScaleCUA
Lite.ScaleCUA grounded teacher trajectories collected on ScaleCUA's OSWorld tasks and judges via the cua-lite lite.scalecua runtime, from two teachers published as separate configs (*.gpt5_5 from gpt-5.5, *.qwen3_8_27b from Qwen/Qwen3.8-27B) and annotated by the same quality pass; ordinary quality gates tagged in metadata.others.exclude_reason, publish-invalid tool leaks/OOB coordinates hard-dropped (filter with not exclude_reason and episode_return>0.5)… See the full description on the dataset page: https://huggingface.co/datasets/cua-lite/Lite.ScaleCUA.Lite.CUAGym
cua-lite/Lite.CUAGym
Lite.CUAGym grounded teacher trajectories collected on CUA-Gym task bundles and reward functions via the cua-lite lite.cuagym runtime, from two teachers published as separate configs (*.gpt5_5 from gpt-5.5, *.qwen3_8_27b from Qwen/Qwen3.8-27B) and annotated by the same quality pass; trajectories kept except /opt/env and OOB-coordinate hard-drops, quality gates tagged in metadata.others.exclude_reason (filter with not exclude_reason and episode_return>0.5)… See the full description on the dataset page: https://huggingface.co/datasets/cua-lite/Lite.CUAGym.CUA-Gym
CUA-Gym
CUA-Gym is a collection of verifiable computer-use agent tasks for reinforcement learning with verifiable rewards (RLVR). Each task pairs a natural-language instruction with executable setup artifacts and a Python reward function that checks task completion programmatically. For details, see the paper CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents.
This release contains the full public CUA-Gym task set after the necessary data review.… See the full description on the dataset page: https://huggingface.co/datasets/xlangai/CUA-Gym.cua-blender