Abstract
Test-Time Policy Optimization enables label-free test-time training for mathematical reasoning by asymmetrically distilling agreeing rollouts and penalizing disagreeing ones, matching supervised performance.
Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models, yet their reliance on ground-truth labels precludes test-time training (TTT). Replacing ground truth with majority-vote pseudo-labels is a natural alternative, yet it is fragile: an incorrect vote corrupts the teacher and misleads every token. We observe that this failure mode is asymmetric: rollouts that disagree with the pseudo-label are typically wrong regardless of whether the vote itself is correct. Building on this observation, we propose Test-Time Policy Optimization (TTPO), an asymmetric objective that distills agreeing rollouts via OPSD and penalizes disagreeing rollouts with Grouped RL. Token-level selection further refines both branches: distillation down-weights already-converged positions, while RL penalizes only confident errors. Both updates remain well-grounded even under frequent pseudo-label errors, and majority-vote routing yields tighter self-supervision as the model improves. Without any labels, TTPO matches label-supervised OPSD on five competition-level benchmarks, raises Qwen3-1.7B from 38.0% to 45.2% in TTT, yields +25.2% to +36.4% without thinking, and shows strong cross-task generalization.
Community
We introduce TTPO, a label-free test-time training framework that remains robust even when majority-vote pseudo-labels are incorrect. TTPO uses an asymmetric objective: it distills agreeing rollouts while penalizing confident errors in disagreeing rollouts through grouped reinforcement learning.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- On-Policy Self-Distillation without Any Supervision (2026)
- Consensus as Privileged Context for Label-Free Self-Distillation (2026)
- Don't Peek at the Answer: Outcome-Masked Group Relative Policy Optimization for Label-Free RLVR (2026)
- On-policy Distillation with Verifiable Reward (2026)
- dOPSD: On-Policy Self-Distillation for Diffusion Language Models (2026)
- Learning from Consensus and Disagreement: Unsupervised On-Policy Self-Distillation with Minority-Trajectory Contrast (2026)
- Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2608.27448 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper