principles.fyi · the brain · concept

RL for reasoning

Rewarding a model for answers that are verifiably right, which teaches it to think step by step.

reward = 1 if the final answer is verifiably correct, else 0

The newest alignment twist (2025–26). Instead of (or on top of) learning from human preferences, the model is rewarded whenever its final answer is verifiably correct — the math checks out, the code runs, the puzzle is solved. Optimizing that reward pushes it to spend more tokens reasoning out loud before committing to an answer. DeepSeek-R1 did this with a method called GRPO and simple rule-based rewards; OpenAI's o-series and the "thinking" modes of Claude and Gemini are the same family. It doesn't slot into a fixed step — it interleaves with or partly replaces classic preference-tuning, and varies by model.