Open Models Almanac
Methodspost-trainingagentic post-training

single mention · post-training

Randomized reasoning-effort level per rollout group

Sampling a reasoning-effort level for each rollout group.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See agentic post-training for the methods filed beside it.

Also called random reasoning effort level.

Filed under post-training › agentic post-training