Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

specific method · filed under post-training

Reinforcement learning from verifiable rewards

Trains with rewards that can be verified, including across a unified mix of environments.

The sources on this page name it without explaining how it works. The line above is the extraction's one-line gloss. See reinforcement learning algorithm for the methods filed beside it.

Also called unified RLVR, RLVR.

sources
4
models
3
lab adopt it
1
strongest
used

Documented in

Evidence

5 quotes from 4 sources, one card per model, each opening with its strongest.

How sources treat it
used 5

We post-train Nemotron 3.5 Super through a comprehensive pipeline spanning Supervised Fine Tuning (SFT), Reinforcement Learning from Verifiable Rewards (RLVR), Reinforcement Learning from Human Feedback (RLHF)

usedpost trainingin Nemotron 3.5 Super and Nemotron 3.5 LightningNVIDIA
1 more from this model

Super’s post-training pipeline combines supervised fine-tuning, Reinforcement Learning from Verifiable Rewards (RLVR)

usedpost trainingin NVIDIA Nemotron 3.5 Super and NVIDIA Nemotron 3.5 LightningNVIDIA

NVIDIA-Nemotron-3-Ultra-550B-A55B

NVIDIAadopted2 sources

we conduct a unified RLVR (Reinforcement Learning with Verifiable Reward) training stage spanning all available environments

usedpost trainingin Nemotron 3 UltraNVIDIA
2 more from this model

followed by unified RLVR over a wide mix of reasoning, agentic, code, safety, usability, and chat environments

usedpost trainingin Nemotron 3 UltraNVIDIA

RLVR (Reinforcement Learning with Verifiable Reward) training stage spanning all available environments

usedoptimizationin Nemotron 3 UltraNVIDIA
↑