A model self-improves on math reasoning by majority-voting its own rollouts, using the winning answer as a pseudo-solution, and distilling itself on the disagreeing rollouts, without any labeled data.
arXiv e-prints , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On-Policy Self-Distillation without Any Supervision
A model self-improves on math reasoning by majority-voting its own rollouts, using the winning answer as a pseudo-solution, and distilling itself on the disagreeing rollouts, without any labeled data.