Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

single mention · post-training

Agentic RL task mix with a shared tool-use API

A prompt distribution spanning code-repository, shell, and tool-integrated math task families through one tool-use API.

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

Filed under post-training › reinforcement learning algorithm