Reasoning with Sampling: Cutting at Decision Points 事件

Reasoning with Sampling: Cutting at Decision Points arXiv:2605.30327v1 Announce Type: cross Abstract: Frontier reasoning models are produced by posttraining base language models with reinforcement learning. Recent work has challenged this by showing that sampling from a sharpened version of the base model's distribution, a so-called power distribution, elicits comparable reasoning without additional training, curated datasets, or verifiers. However, making this method practical requires efficie