specific method · filed under post-training
Pivot Reinforcement Learning
A named RL method used in single-step agentic environments and an MOPD stage; its detailed mechanism is not specified.
Also called PivotRL.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
we ran PivotRL (yi2026pivotrl) on single-step agentic environments
usedoptimizationin SWE teacher for Nemotron 3 UltraNVIDIA
proceeded with pivot RL in the MOPD stage, distilling the SFT-trained teacher into the student Ultra model
usedoptimizationin Nemotron 3 Ultra (office teacher)NVIDIA
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 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 TrainingDropping All-Zero-Advantage Groups