The paper shows that advantage collapse in GRPO causes training stagnation on math reasoning benchmarks and proposes AVSPO, which uses real-time monitoring to inject virtual reward samples and reduces collapse while improving accuracy by 4-6 points.
Curriculum learning
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
-
Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation
The paper shows that advantage collapse in GRPO causes training stagnation on math reasoning benchmarks and proposes AVSPO, which uses real-time monitoring to inject virtual reward samples and reduces collapse while improving accuracy by 4-6 points.