发现大模型推理中自我强化循环陷阱，提出早期预警方法。
Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models
- 识别出模型自洽性错误导致的循环推理现象
- 构建LoopBench数据集验证两种循环模式
- 用累积和算法提前预测循环发生，适合推理优化研究者
尽管测试时缩放取得成功，大型推理模型（LRMs）仍频繁陷入重复循环，造成计算浪费和推理失败。本文识别出一种新型故障模式——循环推理。不同于传统退化，该现象表现为生成内容作为自身逻辑前提引发自我重复，形成无法逃脱的循环。为此，我们构建了LoopBench数据集，用于捕捉数值循环与陈述循环两类模式。机制上，循环推理表现为状态坍塌，其特征是语义重复先于文本重复。我们发现推理瓶颈触发循环启动，并由自增强的V型注意力机制持续维持。基于此，采用累积和（CUSUM）算法捕捉循环前兆，实现早期预测。在多种LRM上的实验验证了其准确性，并揭示长链推理的稳定性边界。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。