← All methodologies

Reinforcement Learning with Verifiable Rewards

RLVR
Practice with an answer checker.

The model tries a task. A checker scores the result. Training makes higher-scoring attempts more likely.

The idea

You practice arithmetic with an answer key. Nobody needs to vote on whether 6 × 7 equals 42. But a tiny answer key cannot test every skill you might need.

The feedback comes from a check, not a vote.

The task

What is 6 × 7?

Attempt A

42

Pass · reward 1
Attempt B

41

Fail · reward 0
Check

Checker compares each answer with 42.

Scores → an RL update

Practice again with the updated model.

A toy answer-key example. Real checks may run code tests or check several requirements. A pass only proves what the checker actually tested.

How RLVR works

  1. Choose checkable tasks

    Use questions with known answers or code with tests.

  2. Generate attempts

    Let the model try answers rather than showing it only the solution.

  3. Run the checker

    Turn the test result into a reward.

  4. Update and repeat

    Use those rewards to adjust the model, then test on unseen tasks.

Useful for

Math answers, coding tasks, and requirements a reliable program can check.

The catch

Weak checks can be exploited. Passing a few tests does not guarantee correct code, and a correct final answer does not prove every reasoning step was sound.

A little more detail

What does “verifiable” mean?

It means there is a defined way to check the result. It does not mean the model becomes correct about everything.

Can RLVR use GRPO?

Yes. RLVR says where the reward comes from. GRPO says how to use rewards to update the model. The two can be used together.

Read the research

These guides simplify the methods. The papers describe the full training recipes. Examples on this page are illustrative, not experimental results.