# Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models arXiv: https://arxiv.org/abs/2601.10679 ยท HTML: https://mlsanity.com/paper/2601.10679/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. - Builds on 25 of its 39 references that are in the map. - First posted on arXiv 15 Jan 2026. ## Placed in - LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/) ## Builds on (most cited first, 25 of 25) - [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021) - [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025) - [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024) - [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018) - [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016) - [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025) - [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025) - [Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs](https://mlsanity.com/paper/2506.14245/) (2025) - [Hierarchical Reasoning Model](https://mlsanity.com/paper/2506.21734/) (2025) - [On the Measure of Intelligence](https://mlsanity.com/paper/1911.01547/) (2019) - [Thought Anchors: Which LLM Reasoning Steps Matter?](https://mlsanity.com/paper/2506.19143/) (2025) - [Recursive Language Models](https://mlsanity.com/paper/2512.24601/) (2025) - [Efficient Reasoning with Hidden Thinking](https://mlsanity.com/paper/2501.19201/) (2025) - [Less is More: Recursive Reasoning with Tiny Networks](https://mlsanity.com/paper/2510.04871/) (2025) - [Entropy After for reasoning model early exiting](https://mlsanity.com/paper/2509.26522/) (2025) - [Do Latent Tokens Think? A Causal and Adversarial Analysis of Chain-of-Continuous-Thought](https://mlsanity.com/paper/2512.21711/) (2025) - [The Geometry of Reasoning: Flowing Logics in Representation Space](https://mlsanity.com/paper/2510.09782/) (2025) - [How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding](https://mlsanity.com/paper/2507.22928/) (2025) - [Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts](https://mlsanity.com/paper/2509.26314/) (2025) - [Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective](https://mlsanity.com/paper/2505.07859/) (2025) - [A Formal Comparison Between Chain of Thought and Latent Thought](https://mlsanity.com/paper/2509.25239/) (2025) - [Hierarchical Reasoning Models: Perspectives and Misconceptions](https://mlsanity.com/paper/2510.00355/) (2025) - [Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning](https://mlsanity.com/paper/2502.04667/) (2025) - [Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning](https://mlsanity.com/paper/2510.10494/) (2025) - [Accelerating Training Speed of Tiny Recursive Models with Curriculum Guided Adaptive Recursion](https://mlsanity.com/paper/2511.08653/) (2025) ## Built on by (most cited first, 10 of 10) - [Probabilistic Tiny Recursive Model](https://mlsanity.com/paper/2605.19943/) (2026) - [Thinking with Looped Flows](https://mlsanity.com/paper/2609.11801/) (2026) - [Loop the Loopies!](https://mlsanity.com/paper/2607.16051/) (2026) - [Energy-guided Recursive Model](https://mlsanity.com/paper/2607.10128/) (2026) - [Steering Recurrent Reasoners at Inference Time with Readout Feedback](https://mlsanity.com/paper/2608.24136/) (2026) - [When Recursive Models Finish Computing](https://mlsanity.com/paper/2609.26487/) (2026) - [Improving Test-Time Scaling with Adaptive Looped Transformers](https://mlsanity.com/paper/2609.35748/) (2026) - [Recursive Vision Language Models for General Symbolic Reasoning](https://mlsanity.com/paper/2608.01534/) (2026) - [Dissecting Hierarchical Reasoning Models: A Mechanistic Study](https://mlsanity.com/paper/2609.22197/) (2026) - [Resample the Answer: Where to Spend Test-Time Compute in Recursive Reasoning](https://mlsanity.com/paper/2610.16427/) (2026) ## Abstract (arXiv) Hierarchical reasoning model (HRM) achieves extraordinary performance on various reasoning tasks, significantly outperforming large language model-based reasoners. To understand the strengths and potential failure modes of HRM, we conduct a mechanistic study on its reasoning patterns and find three surprising facts: (a) Failure of extremely simple puzzles, e.g., HRM can fail on a puzzle with only one unknown cell. We attribute this failure to the violation of the fixed point property, a fundamental assumption of HRM. (b) "Grokking" dynamics in reasoning steps, i.e., the answer is not improved uniformly, but instead there is a critical reasoning step that suddenly makes the answer correct; (c) Existence of multiple fixed points. HRM "guesses" the first fixed point, which could be incorrect, and gets trapped there for a while or forever. All facts imply that HRM appears to be "guessing" instead of "reasoning". Leveraging this "guessing" picture, we propose three strategies to scale HRM's guesses: data augmentation (scaling the quality of guesses), input perturbation (scaling the number of guesses by leveraging inference randomness), and model bootstrapping (scaling the number of guesses by leveraging training randomness). On the practical side, by combining all methods, we develop Augmented HRM, boosting accuracy on Sudoku-Extreme from 54.5% to 96.9%. On the scientific side, our analysis provides new insights into how reasoning models "reason".