# Is my model "mind blurting"? Interpreting the dynamics of reasoning tokens with Recurrence Quantification Analysis (RQA)

arXiv: https://arxiv.org/abs/2602.06266 · HTML: https://mlsanity.com/paper/2602.06266/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 13 of 13)

- [ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning](https://mlsanity.com/paper/2502.01100/) (2025)
- [Thought Anchors: Which LLM Reasoning Steps Matter?](https://mlsanity.com/paper/2506.19143/) (2025)
- [Understanding Reasoning in Thinking Language Models via Steering Vectors](https://mlsanity.com/paper/2506.18167/) (2025)
- [How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning](https://mlsanity.com/paper/2402.18312/) (2024)
- [What's the Magic Word? A Control Theory of LLM Prompting](https://mlsanity.com/paper/2310.04444/) (2023)
- [Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!](https://mlsanity.com/paper/2504.09762/) (2025)
- [Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models](https://mlsanity.com/paper/2402.07754/) (2024)
- [How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding](https://mlsanity.com/paper/2507.22928/) (2025)
- [ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models](https://mlsanity.com/paper/2503.22048/) (2025)
- [Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer](https://mlsanity.com/paper/2409.09239/) (2024)
- [Exploring Information Processing in Large Language Models: Insights from Information Bottleneck Theory](https://mlsanity.com/paper/2501.00999/) (2025)
- [A Statistical Physics of Language Model Reasoning](https://mlsanity.com/paper/2506.04374/) (2025)
- [Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations](https://mlsanity.com/paper/2502.12530/) (2025)

## Built on by (most cited first, 1 of 1)

- [Interpreting Latent CoT Reasoning as Dynamical Systems](https://mlsanity.com/paper/2607.09698/) (2026)

## Abstract (arXiv)

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.