Sampling multiple reasoning paths, refining each with self-critique and self-correction, then majority voting improves math reasoning accuracy over width-only or verifier-based test-time scaling on several open-weight LLMs.
International Conference on Learning Representations , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning
Sampling multiple reasoning paths, refining each with self-critique and self-correction, then majority voting improves math reasoning accuracy over width-only or verifier-based test-time scaling on several open-weight LLMs.