Model techniques map
Techniquespost-trainingreinforcement learning algorithm

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.