@inproceedings{wang-etal-2025-wait,
    title = "Wait, We Don{'}t Need to ``Wait''! Removing Thinking Tokens Improves Reasoning Efficiency",
    author = "Wang, Chenlong  and
      Feng, Yuanning  and
      Chen, Dongping  and
      Chu, Zhaoyang  and
      Krishna, Ranjay  and
      Zhou, Tianyi",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.394/",
    doi = "10.18653/v1/2025.findings-emnlp.394",
    pages = "7459--7482",
    ISBN = "979-8-89176-335-7",
    abstract = "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."
}