DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes 事件

DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes arXiv:2605.28421v1 Announce Type: new Abstract: Reinforcement learning has become a central paradigm for advancing reasoning in large language models, yet most existing methods still depend on stronger teacher models or heavily curated difficult datasets, limiting scalable capability improvement. In this paper, we introduce DenoiseRL, a reinforcement learning framework that substitutes external supervision with recovery-or