Paper summary
Paper summary: Reinforcement Learning for Reasoning in Large Language Models with One Training Example
RL with verifiable rewards on a single maths training example lifts Qwen2.5-Math-1.5B on MATH500 from 36.0% to 73.6%, matching training on a 1.2k-example dataset.
- One carefully chosen training example produced most of the gain of a 1,200-example RL dataset.
- The authors separate the real gain from mere output-format correction.