@inproceedings{zhang-etal-2026-llms,
    title = "Do {LLM}s Really Need 10+ Thoughts for ``Find the Time 1000 Days Later''? Towards Structural Understanding of {LLM} Overthinking",
    author = "Zhang, Xinliang Frederick  and
      Mohananey, Anhad  and
      Chronopoulou, Alexandra  and
      Papalampidi, Pinelopi  and
      Gupta, Somit  and
      Munkhdalai, Tsendsuren  and
      Wang, Lu  and
      Upadhyay, Shyam",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.773/",
    pages = "17005--17030",
    ISBN = "979-8-89176-390-6",
    abstract = "Models employing long chain-of-thought (CoT) reasoning have shown superior performance on complex reasoning tasks. Yet, this capability introduces a critical and often overlooked inefficiency{---}overthinking{---}models often engage in unnecessarily extensive reasoning even for simple queries, incurring significant computations without accuracy improvements. While prior work has explored solutions to mitigate overthinking, a fundamental gap remains in our understanding of its underlying causes. Most existing analyses are limited to superficial, profiling-based observations, failing to delve into LLMs' inner workings. This study introduces a systematic, fine-grained analyzer of LLMs' thought process to bridge the gap, TRACE. We first benchmark the overthinking issue, confirming that long-thinking models are five to twenty times slower on simple tasks with no substantial gains. We then use TRACE to first decompose the thought process into minimally complete sub-thoughts. Next, by inferring discourse relationships among sub-thoughts, we construct granular thought progression graphs and subsequently identify common thinking patterns for topically similar queries. Our analysis reveals two major patterns for open-weight thinking models{---}Explorer and Late Landing. This finding provides evidence that over-verification and over-exploration are the primary drivers of overthinking in LLMs. Grounded in thought structures, we propose a utility-based definition of overthinking, which moves beyond length-based metrics. This revised definition offers a more insightful understanding of LLMs' thought progression, as well as practical guidelines for principled overthinking management."
}