arXiv:2604.10739v1 Announce Type: new
Abstract: Scaling test-time compute through extended chains of thought has become a dominant paradigm for improving large language model reasoning. However, existing research implicitly assumes that longer thinking always yields better results. This assumption remains largely unexamined. We systematically investigate how the marginal utility of additional reasoning tokens changes as compute budgets increase. We find that marginal returns diminish substantially at higher budgets and that models exhibit “overthinking”, where extended reasoning is associated with abandoning previously correct answers. Furthermore, we show that optimal thinking length varies across problem difficulty, suggesting that uniform compute allocation is suboptimal. Our cost-aware evaluation framework reveals that stopping at moderate budgets can reduce computation significantly while maintaining comparable accuracy.
Measuring and reducing surgical staff stress in a realistic operating room setting using EDA monitoring and smart hearing protection
BackgroundStress is a critical factor in the operating room (OR) and affects both the performance and well-being of surgical staff. Measuring and mitigating this stress