CoDistill-GRPO lets small and large models mutually improve via co-distillation in GRPO, raising small-model math accuracy by over 11 points while cutting large-model training time by about 18%.
Second Conference on Language Modeling , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Outcome-level RL with binary or composite rewards improves compositional generalization over supervised fine-tuning by avoiding overfitting to frequent training patterns.
citing papers explorer
-
CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization
CoDistill-GRPO lets small and large models mutually improve via co-distillation in GRPO, raising small-model math accuracy by over 11 points while cutting large-model training time by about 18%.
-
Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization
Outcome-level RL with binary or composite rewards improves compositional generalization over supervised fine-tuning by avoiding overfitting to frequent training patterns.