SOURCE-LINKED INTELLIGENCE

GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Post-training plays a pivotal role in enhancing the reasoning capabilities and task-specific expertise of large language models (LLMs). Despite recent advances in post-training methods, such as Group Relative Policy Optimization (GRPO), their practical deployment remains impeded by training instability arising from the reliance on importance sampling. We introduce Group Variance Policy Optimization (GVPO), a novel post-training method that integrates the analytical solution of KL-constrained reward maximization into its gradient weighting scheme. This formulation provides an intuitive interpre

Read original source ↗ Open in workspace

recordType

paper

region

Global