MUR: Momentum Uncertainty guided Reasoning for Large Language Models 事件

MUR: Momentum Uncertainty guided Reasoning for Large Language Models arXiv:2507.14958v5 Announce Type: replace Abstract: Large Language Models have achieved impressive performance on reasoning-intensive tasks, yet optimizing their reasoning efficiency remains an open challenge. While Test-Time Scaling (TTS) improves reasoning quality, it often leads to overthinking, wasting tokens on redundant computations. This work investigates how to efficiently and adaptively guide current model' test-time