No AI summary available for this article.
Why It Matters
Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches typically optimize a large fraction of the model parameters.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches typically optimize a large fraction of the model parameters. This raises a natural question: can effective test-time adaptation emerge when both the reward signal and the optimization space are severely restricted? We answer this question with label-free bias-only TTRL, which uses majority-vote pseudo-labels as rewards and optimizes only approximately 100K bias parameters while keeping the pretrained backbone frozen. On MATH-500, our approach reach...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.18587v1 · Indexed about 1 hour ago