1
CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
提出CurveRL方法，通过分布感知的上下文重加权提升LLM推理性能，理论严谨效果显著。
arXiv:2605.24331v1 Announce Type: new Abstract: Context or prompt-level reweighting has emerged as a central algorithmic lever in Reinforcement Learni…