@inproceedings{wei-etal-2026-evolution,
    title = "The Evolution of Thought: Tracking {LLM} Overthinking via Reasoning Dynamics Analysis",
    author = "Wei, Zihao  and
      Pang, Liang  and
      Liu, Jiahao  and
      Shi, Wenjie  and
      Deng, Jingcheng  and
      Xu, Shicheng  and
      Duan, Zenghao  and
      Wang, Jingang  and
      Sun, Fei  and
      Shen, Huawei  and
      Cheng, Xueqi",
    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.1239/",
    pages = "26905--26920",
    ISBN = "979-8-89176-390-6",
    abstract = "Test-time scaling via explicit reasoning trajectories significantly boosts large language model (LLM) performance but often triggers overthinking. To explore this, we analyze reasoning through two lenses: Reasoning Length Dynamics, which reveals a compensatory trade-off between thinking and answer content length that eventually leads to thinking redundancy, and Reasoning Semantic Dynamics, which identifies semantic convergence and repetitive oscillations. These dynamics uncover an instance-specific Reasoning Completion Point (RCP), beyond which computation continues without further performance gain. Since the RCP varies across instances, we propose a Reasoning Completion Point Detector (RCPD), an inference-time early-exit method that identifies the RCP by monitoring the rank dynamics of termination tokens (e.g., lt;/think gt;). Across AIME and GPQA benchmarks using Qwen3 and DeepSeek-R1, RCPD reduces token usage by up to 44{\%} while preserving accuracy, offering a principled approach to efficient test-time scaling."
}