Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

single mention · post-training

MiMo-style segment-level advantage correction

Corrects advantages at the segment level for turns flagged for generation issues such as format violations or invalid tool calls.

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