Use GRPO with verifiable rewards (RLVR) to lift reasoning with fewer than 100 examples

LLM-Stats·medium signal

GRPO — the algorithm behind DeepSeek-R1 — drops the separate critic network and instead generates multiple completions per prompt and grades them relative to each other, making RL fine-tuning cheap enough to run on small data. Paired with Reinforcement Learning with Verifiable Rewards (rule-based verifiers for tasks with checkable outcomes), it can improve reasoning with under 100 training examples. Reach for it when your task has a programmatic correctness check (tests pass, math verifies, format validates) rather than a fuzzy quality target.