Preprint Open access
Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA
Test-time reinforcement learning adapts a model on its own unlabeled test set using majority-vote pseudo-labels and has shown strong results in mathematics. We show that this recipe collapses on medical multiple-choice QA: accuracy stagnates while output diversity rapidly declines. Through a controlled experiment that …