Open Models Almanac
Methodspost-trainingreward modelling

single mention · post-training

Agentic Generative Reward Model

Uses an agentic generative reward model with tournament-style binary comparisons to score non-verifiable general tasks.

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

Also called Agentic Generative Reward Model (GRM).

Filed under post-training › reward modelling