1
OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
大模型推理新突破：在线策略自蒸馏结合结果引导的logit转向，有效提升推理性能。
arXiv:2605.12400v2 Announce Type: replace Abstract: We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability…