@inproceedings{shen-etal-2025-dast,
    title = "{DAST}: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models",
    author = "Shen, Yi  and
      Zhang, Jian  and
      Huang, Jieyun  and
      Shi, Shuming  and
      Zhang, Wenjing  and
      Yan, Jiangze  and
      Wang, Ning  and
      Wang, Kai  and
      Liu, Zhaoxiang  and
      Lian, Shiguo",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.160/",
    pages = "2322--2331",
    ISBN = "979-8-89176-333-3",
    abstract = "Recent advancements in slow-thinking reasoning models have shown exceptional performance in complex reasoning tasks. However, their tendency for ``overthinking'' on simple problems leads to excessive computational resource usage and increased inference latency, which hinders their widespread industrial adoption. While current mitigation strategies uniformly reduce reasoning tokens, they risk degrading performance on challenging tasks that require extended reasoning. This paper introduces Difficulty-Adaptive Slow-Thinking (DAST), a novel framework that enables models to autonomously adjust Chain-of-Thought (CoT) length based on problem difficulty. We propose a Token Length Budget (TLB) metric and leverage budget-aware preference optimization to implement DAST, which penalizes inefficiency on simple problems while incentivizing deep reasoning for complex ones. Experiments demonstrate DAST{'}s significant value for practical application: it effectively mitigates overthinking, substantially lowering costs and latency{---}while crucially preserving high accuracy on complex problems, paving the way for the efficient application of advanced reasoning models."
}