PathCal calibrates reasoning paths by type-aware soft rebalancing of reflection-marker logits at uncertain states, yielding better efficiency-performance trade-offs on six benchmarks.
Chi, Quoc V Le, and Denny Zhou
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
LUFFY mixes off-policy reasoning traces into RLVR training via Mixed-Policy GRPO and regularized importance sampling, delivering over 6-point gains on math benchmarks and enabling training of weak models where on-policy RLVR fails.
citing papers explorer
-
PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
PathCal calibrates reasoning paths by type-aware soft rebalancing of reflection-marker logits at uncertain states, yielding better efficiency-performance trade-offs on six benchmarks.
-
Learning to Reason under Off-Policy Guidance
LUFFY mixes off-policy reasoning traces into RLVR training via Mixed-Policy GRPO and regularized importance sampling, delivering over 6-point gains on math benchmarks and enabling training of weak models where on-policy RLVR fails.