SHAPE improves average math reasoning accuracy by 3% while cutting token use by 30% through stage-aware hierarchical advantage and entropy-driven token redistribution.
(14) Solving forα, we obtain the sufficient condition: α <0.5(15) This derivation proves that by setting α <0.5 , the dense outcome signal ( Routcome) serves as a dominant anchor
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning
SHAPE improves average math reasoning accuracy by 3% while cutting token use by 30% through stage-aware hierarchical advantage and entropy-driven token redistribution.