等等，我们不需要“等待”！移除思考令牌提升推理效率
Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency
AI总结：
针对大型推理模型过度思考导致效率低下的问题，提出NoWait方法，通过抑制“Wait”等思考令牌，在十个基准上减少思维链长度27%-51%且不损效用。
摘要：
大型推理模型的最新进展实现了复杂、逐步的推理，但往往引入显著的过度思考，导致输出冗长冗余，妨碍效率。本研究探讨了由“Wait”和“Hmm”等令牌标记的显式自我反思，对于高级推理是否必要。我们提出NoWait，一种简单而有效的方法，通过在推理过程中抑制这些令牌来禁用显式自我反思。在十个基准上跨文本、视觉和视频推理任务的广泛实验表明，NoWait在五个R1风格模型系列中将思维链轨迹长度减少高达27%-51%，且不损害模型效用。因此，NoWait为高效且保持效用的多模态推理提供了即插即用的解决方案。
英文摘要：
Recent advances in large reasoning models have enabled complex, step-by-step reasoning but often introduce significant overthinking, resulting in verbose and redundant outputs that hinder efficiency. In this study, we examine whether explicit self-reflection, signaled by tokens such as "Wait" and "Hmm", is necessary for advanced reasoning. We propose NoWait, a simple yet effective approach that disables explicit self-reflection by suppressing these tokens during inference. Extensive experiments on ten benchmarks across textual, visual, and video reasoning tasks show that NoWait reduces chain-of-thought trajectory length by up to 27%-51% in five R1-style model series, without compromising model utility. NoWait thus offers a plug-and-play solution for efficient and utility-preserving multimodal reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
