AI RESEARCH
MUR: Momentum Uncertainty guided Reasoning
arXiv CS.CL
•
ArXi:2507.14958v3 Announce Type: replace Current 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 scaling without additional