Despite the success of test-time scaling, Large Reasoning Models (LRMs) frequently encounter repetitive loops that lead to computational waste and inference failure. In this paper, we identify a distinct failure mode termed Circular Reasoning. Unlike traditional model degeneration, this phenomenon manifests as a self-reinforcing trap where generated content acts as a logical premise for its own recurrence, compelling the reiteration of preceding text. To systematically analyze this phenomenon, we introduce LoopBench, a dataset designed to capture two distinct loop typologies: numerical loops and statement loops. Mechanistically, we characterize circular reasoning as a state collapse exhibiting distinct boundaries, where semantic repetition precedes textual repetition. We reveal that reasoning impasses trigger the loop onset, which subsequently persists as an inescapable cycle driven by a self-reinforcing V-shaped attention mechanism. Guided by these findings, we employ the Cumulative Sum (CUSUM) algorithm to capture these precursors for early loop prediction. Experiments across diverse LRMs validate its accuracy and elucidate the stability of long-chain reasoning.

翻译：尽管测试时扩展取得了成功，大型推理模型（LRMs）仍频繁遭遇重复循环，导致计算资源浪费与推理失败。本文识别出一种独特的失效模式，称为“循环推理”。与传统模型退化不同，该现象表现为一种自我强化的陷阱：模型生成的内容作为其自身重复的逻辑前提，迫使先前文本被不断复述。为系统分析此现象，我们引入了LoopBench数据集，该数据集旨在捕捉两种不同的循环类型：数值循环与陈述循环。在机制层面，我们将循环推理特征化为具有清晰边界的状态坍缩，其中语义重复先于文本重复出现。我们发现推理僵局会触发循环起始，随后在自我强化的V形注意力机制驱动下，该循环将作为无法逃脱的周期持续存在。基于这些发现，我们采用累积和（CUSUM）算法捕捉这些先兆以实现早期循环预测。跨多种LRMs的实验验证了该方法的准确性，并阐明了长链推理的稳定性。