OSWorld
Public[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
agentartificial-intelligencebenchmarkclicode-generationguilanguage-modellarge-action-modelllmmultimodal
Creat:2023-10-16T09:49:13
Update:2025-03-26T17:06:46
https://os-world.github.io
2.0K
Stars
5
Stars Increase