用数学方法分析大模型推理时的思维动态，比看回答长短更准。
Is my model "mind blurting"? Interpreting the dynamics of reasoning tokens with Recurrence Quantification Analysis (RQA)
- 把生成文本看作动态系统，用RQA分析每一步隐向量的变化模式。
- 发现RQA能捕捉长度无法反映的推理信号，提升任务复杂度预测准确率8%。
- 适合研究模型推理机制或测试时扩展规律的研究者使用。
测试时计算对大型推理模型至关重要，但通过生成文本分析其推理行为日益困难且不可靠。响应长度常被用作推理努力的粗略代理，但该指标无法捕捉思维链（CoT）或生成标记的动态与效率。本文提出利用递归量化分析（RQA）作为非文本化方法，在测试时分析模型推理链。将标记生成视为动态系统，提取每步生成的隐藏嵌入，并对所得轨迹应用RQA。RQA指标如确定性（Determinism）和层化度（Laminarity）量化了模型潜在表示中的重复与停滞模式。通过对DeepSeek-R1-Distill的3,600条生成轨迹分析，发现RQA捕捉到了响应长度未反映的信号，并使任务复杂度预测准确率提升8%。这些结果确立了RQA作为研究推理模型测试时扩展中潜在标记生成动态的可靠工具。
原文摘要 · Abstract (English)
Test-time compute is central to large reasoning models, yet analysing their reasoning behaviour through generated text is increasingly impractical and unreliable. Response length is often used as a brute proxy for reasoning effort, but this metric fails to capture the dynamics and effectiveness of the Chain of Thoughts (CoT) or the generated tokens. We propose Recurrence Quantification Analysis (RQA) as a non-textual alternative for analysing model's reasoning chains at test time. By treating token generation as a dynamical system, we extract hidden embeddings at each generation step and apply RQA to the resulting trajectories. RQA metrics, including Determinism and Laminarity, quantify patterns of repetition and stalling in the model's latent representations. Analysing 3,600 generation traces from DeepSeek-R1-Distill, we show that RQA captures signals not reflected by response length, but also substantially improves prediction of task complexity by 8\%. These results help establish RQA as a principled tool for studying the latent token generation dynamics of test-time scaling in reasoning models.
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。