specific method · filed under post-training
Keep Candidate-Set Replay
Recording each token's rollout candidate set and renormalizing training log-probabilities within that set.
Also called candidate-set replay.
- source
- 1
- models
- 2
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
we record each token’s candidate set during rollout and renormalize the training log-probabilities within it, matching the sampler’s normalization.
usedsoftware implementationin MiMo-V2.6Xiaomi
Filed alongside
Other methods under post-training :: reinforcement learning algorithm.
Group Relative Policy OptimizationReinforcement LearningGroupwise Advantage RedistributionFreezing the MoE Router During Reinforcement LearningIcePopOff-Policy Sequence MaskingReinforcement Learning from Verifiable RewardsRollout Routing ReplayUnbiased KL EstimateAsynchronous Group Relative Policy OptimizationChain-of-Thought Reinforcement LearningDirect Double-Sided Importance SamplingKeep Sampling MaskMixed Reinforcement LearningPivot Reinforcement LearningReinforcement Learning Post-TrainingAbstention TrainingAdvantage ShapingAgentic RL Task MixCISPO with Length-Weighted Leave-One-Out Group-Relative AdvantagesConcatenated Routing ReplayDerived-Latency PenaltyDomain-Specialized RL ExpertsDomain-Specific GRPO Training