GCPO uses team-level credit assignment via determinant volume over reward-weighted semantic embeddings to promote non-redundant correct reasoning paths, improving both accuracy and diversity in LLM training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning
GCPO uses team-level credit assignment via determinant volume over reward-weighted semantic embeddings to promote non-redundant correct reasoning paths, improving both accuracy and diversity in LLM training.