←Back to the radar
SOTA · agents
Agents
Multi-step tool use, web/OS tasks, long-horizon autonomy
RULERWebArena, OSWorld, GAIA, multi-step tool tasks
The ladder
0Nothing in this domain has cleared our inclusion gate yet. The gate: a verifiable measurement or a reproducible demo — keynote screenshots do not qualify.
Assets you can use now
No installable skill wired to this domain yet.
Verticals using it
No content maps this capability to a vertical yet.
Boundaries & failure modes
The boundary note for this domain is not written yet. It should answer three things: where it is stuck, under which conditions it breaks, and the order of magnitude of cost and latency. Until it lands, a ladder position only says this asset leads on our ruler — not that it works on your task.