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., </think>). 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.
@article{arxiv.2508.17627,
title = {The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis},
author = {Zihao Wei and Liang Pang and Jiahao Liu and Wenjie Shi and Jingcheng Deng and Shicheng Xu and Zenghao Duan and Fei Sun and Huawei Shen and Xueqi Cheng},
journal= {arXiv preprint arXiv:2508.17627},
year = {2026}
}