# Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs

arXiv: https://arxiv.org/abs/2506.07240 · HTML: https://mlsanity.com/paper/2506.07240/

## Key facts

- Cited by 22 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 16 of its 32 references that are in the map.
- First posted on arXiv 8 Jun 2025.

## 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, 16 of 16)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [When More is Less: Understanding Chain-of-Thought Length in LLMs](https://mlsanity.com/paper/2502.07266/) (2025)
- [Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs](https://mlsanity.com/paper/2501.18585/) (2025)
- [The Impact of Reasoning Step Length on Large Language Models](https://mlsanity.com/paper/2401.04925/) (2024)
- [From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models](https://mlsanity.com/paper/2406.16838/) (2024)
- [Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs](https://mlsanity.com/paper/2505.00127/) (2025)
- [Effectively Controlling Reasoning Models through Thinking Intervention](https://mlsanity.com/paper/2503.24370/) (2025)
- [Zero-Shot Strategies for Length-Controllable Summarization](https://mlsanity.com/paper/2501.00233/) (2024)

## Built on by (most cited first, 22 of 22)

- [Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models](https://mlsanity.com/paper/2508.02120/) (2025)
- [SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding](https://mlsanity.com/paper/2511.00606/) (2025)
- [Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2507.09662/) (2025)
- [Predicting LLM Output Length via Entropy-Guided Representations](https://mlsanity.com/paper/2602.11812/) (2026)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process](https://mlsanity.com/paper/2512.23988/) (2025)
- [From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning](https://mlsanity.com/paper/2606.18089/) (2026)
- [Steering Large Reasoning Models towards Concise Reasoning via Flow Matching](https://mlsanity.com/paper/2602.05539/) (2026)
- [NEAT: Neuron-Based Early Exit for Large Reasoning Models](https://mlsanity.com/paper/2602.02010/) (2026)
- [Limited Reasoning Space: The cage of long-horizon reasoning in LLMs](https://mlsanity.com/paper/2602.19281/) (2026)
- [DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning](https://mlsanity.com/paper/2606.15160/) (2026)
- [Adaptive Overclocking: Dynamic Control of Thinking Path Length via Real-Time Reasoning Signals](https://mlsanity.com/paper/2509.17000/) (2025)
- [Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces](https://mlsanity.com/paper/2605.14358/) (2026)
- [Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking](https://mlsanity.com/paper/2605.27712/) (2026)
- [Metacognition in LLMs: Foundations, Progress, and Opportunities](https://mlsanity.com/paper/2607.11881/) (2026)
- [SABER: Stability-Aware Early Exit for LLM Reasoning via Adversarial Branch Probing](https://mlsanity.com/paper/2608.27963/) (2026)
- [OUTLETS: Output-Length Prediction from Speculative Decoding Backbones](https://mlsanity.com/paper/2609.01068/) (2026)
- [On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing](https://mlsanity.com/paper/2609.07681/) (2026)
- [To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals](https://mlsanity.com/paper/2609.20186/) (2026)
- [Spatiotemporal Hidden-State Dynamics as a Signature of Internal Reasoning in Large Language Models](https://mlsanity.com/paper/2605.01853/) (2026)
- [Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training](https://mlsanity.com/paper/2605.11416/) (2026)
- [Adaptive Triggering for Bias Correction in LLM Reasoning](https://mlsanity.com/paper/2608.25379/) (2026)

## Abstract (arXiv)

Recently, techniques such as explicit structured reasoning have demonstrated strong test-time scaling behavior by enforcing a separation between the model's internal "thinking" process and the final response. A key factor influencing answer quality in this setting is the length of the thinking stage. When the reasoning is too short, the model may fail to capture the complexity of the task. Conversely, when it is too long, the model may overthink, leading to unnecessary computation and degraded performance. This paper explores and exploits the underlying mechanisms by which LLMs understand and regulate the length of their reasoning during explicit thought processes. First, we show that LLMs encode their progress through the reasoning process and introduce an interactive progress bar visualization, which is then used to reveal insights on the model's planning dynamics. Second, we manipulate the internal progress encoding during inference to reduce unnecessary steps and generate a more concise and decisive chain of thoughts. Our empirical results demonstrate that this "overclocking" method mitigates overthinking, improves answer accuracy, and reduces inference latency. Our code is publicly available.