Open Models Almanac
Methodspost-trainingagentic post-training

single mention · post-training

Large-scale reinforcement learning on synthetic agentic data

Large-scale RL trained on synthetic data, with reported gains on agentic benchmarks.

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 large-scale RL on synthetic data.

Filed under post-training › agentic post-training