Model techniques map
Techniquespost-trainingreinforcement learning algorithm

specific method · filed under post-training

Groupwise Advantage Redistribution

An online method that ranks passing trajectories within a group and redistributes positive advantage toward higher-quality solutions.

Also called Groupwise Advantage Redistribution (GAR).

sources
3
models
2
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 3core 1

Documented in

Evidence

4 spans quoted from the sources, strongest treatment first.

Groupwise Advantage Redistribution (GAR) ranks passing trajectories online and moves advantage toward higher-quality solutions.

coreoptimizationin MiMo-V2.6-Flash-RLXiaomi

Groupwise Advantage Redistribution (GAR) ranks passing trajectories online and moves advantage toward higher-quality solutions.

usedoptimizationin MiMo-V2.6-Pro-RLXiaomi

Through our proposed Groupwise Reward Synthesis (GRS) and Groupwise Advantage Redistribution (GAR), these fine-grained distinctions are converted into more informative learning signals

usedtraining objectivein MiMo-V2.6 RL trainingXiaomi

Its online agentic grader jointly examines successful and failed trajectories within each mixed-outcome group, ranks passing solutions, and redistributes positive advantage toward higher-quality passing trajectories.

usedpost trainingin MiMo-V2.6-Pro and MiMo-V2.6-FlashXiaomi

Filed alongside

Other methods under post-training :: reinforcement learning algorithm.