Open Models Almanac
Methodspost-trainingrollout & RL infrastructure

single mention · post-training

Agent Loop

An execution loop that owns an environment lifecycle, manages dialogue, and invokes inference on demand.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See rollout & RL infrastructure for the methods filed beside it.

Filed under post-training › rollout & RL infrastructure