SOURCE-LINKED INTELLIGENCE

Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global