DeepSeek-R1: Incentivizing Reasoning via RL (RLVR)

Editorial record

Plain-language summary

The team applied reinforcement learning where the reward comes from verifying the final result (a math answer being correct or code passing tests) rather than from human preference labels. Under this pressure the model learned on its own to write longer reasoning, check its work, and backtrack, with a pure-RL variant (R1-Zero) developing these behaviors from a base model before a small amount of supervised data was added for readability. This demonstrated that reinforcement learning with verifiable rewards (RLVR) is a scalable path to reasoning models, and the released weights made such training widely reproducible.