Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Compares base models and models trained with verifiable rewards on reasoning tasks. Pass@k and solution-distribution analyses distinguish improved sampling efficiency from the emergence of new reasoning patterns.

Compares base models and models trained with verifiable rewards on reasoning tasks. Pass@k and solution-distribution analyses distinguish improved sampling efficiency from the emergence of new reasoning patterns.

When reading the original paper, identify its problem, inputs, outputs, and methodological assumptions.

Compares base models and models trained with verifiable rewards on reasoning tasks. Pass@k and solution-distribution analyses distinguish improved sampling efficiency from the emergence of new reasoning patterns.

Check the baselines, datasets, evaluation protocol, and ablations in the original paper. This directory overview does not provide an independent evaluation or experimental results table.