CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning 事件

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning arXiv:2605.28742v1 Announce Type: new Abstract: Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) approaches to doing so typically require hundreds of training samples and thousands of model rollouts, making them expensive in the best case and intractable in the worst. To address this challenge, we intro