MetaStone-S1 combines a shared policy and self-supervised process reward head to select high-quality reasoning traces, reaching o3-mini-level scores at 32B parameters.
Accessed: 2025-02-18
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Test-Time Scaling with Reflective Generative Model
MetaStone-S1 combines a shared policy and self-supervised process reward head to select high-quality reasoning traces, reaching o3-mini-level scores at 32B parameters.