we explore test-time scaling through parallel agent execution and self-verification, improving Terminal-Bench 2.1 from 62.7% to 71.9%
general family · filed under inference & serving
Parallel test-time compute scaling
Test-time compute is increased by running inference trajectories or agents in parallel.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reasoning control for the methods filed beside it.
Also called in parallel.
Documented in
Evidence
2 quotes from 2 sources, one card per model, each opening with its strongest.
How sources treat it
evaluated 2
evaluatedinference servingin Nemotron 3.5 SuperNVIDIA