SAS stabilizes efficient LLM reasoning by step-level advantage masking, improving Pass@1 accuracy by 0.86 points and cutting reasoning length by 16.3% versus length-aware baselines.
arXiv preprint arXiv:2510.11620
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Stabilizing Efficient Reasoning with Step-Level Advantage Selection
SAS stabilizes efficient LLM reasoning by step-level advantage masking, improving Pass@1 accuracy by 0.86 points and cutting reasoning length by 16.3% versus length-aware baselines.