AI Vocabulary · 01 The Model
What is RLVR?
Reinforcement learning with verifiable rewards: a program checks whether the model's answer is correct, and the model is rewarded only for answers that pass.
In RLVR a program judges the answer: it checks whether a maths result is right or whether code passes its tests. The model then learns through reinforcement learning to produce answers that pass the check. The Allen Institute for AI gave the method its name in 2024.
Andrej Karpathy describes RLVR as the major new training stage of 2025. It delivered much capability per dollar and drew compute away from pretraining. It is a main ingredient of reasoning models.
Why it matters for you
RLVR explains why models improved fastest at maths and programming: those are the fields where answers can be checked automatically. It also explains uneven skills, since tasks without a clear right answer benefit less.
Own it
If your task has checkable answers, such as data extraction with a known format or code with tests, current models are likely strong at it. For judgement tasks, build your own evals with human review.
Where it comes from
The term was introduced in Tulu 3: Pushing Frontiers in Open Language Model Post-Training by Lambert and colleagues at the Allen Institute for AI (2024). Karpathy's assessment is in his 2025 LLM Year in Review.
Related
Your AI Learning Hub
Learn the whole AI Vocabulary, step by step, and build with it. Build it. Own it.