Loading...
RL from Verifiable Rewards (RLVR)
Trains reasoning models with reinforcement learning against automatically checkable rewards, such as whether a math answer matches ground truth or code passes its tests, rather than against learned preference models. Because the reward only scores final correctness, long chains of thought with backtracking and self-verification emerge without supervised rationales. This is distinct from RLHF, RLAIF, and DPO, which optimize human or AI preferences.
Loading technique guide…
RL from Verifiable Rewards (RLVR)
Trains reasoning models with reinforcement learning against automatically checkable rewards, such as whether a math answer matches ground truth or code passes its tests, rather than against learned preference models. Because the reward only scores final correctness, long chains of thought with backtracking and self-verification emerge without supervised rationales. This is distinct from RLHF, RLAIF, and DPO, which optimize human or AI preferences.
Loading technique guide…