Technologies
OSWorld
A benchmark for evaluating AI agents that perform real computer tasks.
0 stories.
Every story about OSWorld (0)
No story is about OSWorld yet: the ones below only mention it.
Also mentioned in (1)
Stories about something else that name OSWorld in passing, with the sentence that does.
- LEASH helps AI agents know when to ask for help“Tests on OSWorld, a benchmark for AI agents that complete computer tasks, used four contemporary model backbones.”