# Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation

arXiv: https://arxiv.org/abs/2510.02249 · HTML: https://mlsanity.com/paper/2510.02249/

## Key facts

- Cited by 4 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 21 of its 40 references that are in the map.
- First posted on arXiv 2 Oct 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, 21 of 21)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2505.22617/) (2025)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Chain of Draft: Thinking Faster by Writing Less](https://mlsanity.com/paper/2502.18600/) (2025)
- [Dynamic Early Exit in Reasoning Models](https://mlsanity.com/paper/2504.15895/) (2025)
- [GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models](https://mlsanity.com/paper/2504.09696/) (2025)
- [Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency](https://mlsanity.com/paper/2506.08343/) (2025)
- [Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL](https://mlsanity.com/paper/2505.10832/) (2025)
- [Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models](https://mlsanity.com/paper/2508.02120/) (2025)
- [One-shot Entropy Minimization](https://mlsanity.com/paper/2505.20282/) (2025)
- [Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression](https://mlsanity.com/paper/2508.05337/) (2025)
- [Lost at the Beginning of Reasoning](https://mlsanity.com/paper/2506.22058/) (2025)
- [ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization](https://mlsanity.com/paper/2506.10822/) (2025)
- [Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning](https://mlsanity.com/paper/2508.02178/) (2025)
- [Multi-Layer GRPO: Enhancing Reasoning and Self-Correction in Large Language Models](https://mlsanity.com/paper/2506.04746/) (2025)
- [Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories](https://mlsanity.com/paper/2507.00711/) (2025)
- [Multimodal Mathematical Reasoning with Diverse Solving Perspective](https://mlsanity.com/paper/2507.02804/) (2025)

## Built on by (most cited first, 4 of 4)

- [Offline Exploration-Aware Fine-Tuning for Long-Chain Mathematical Reasoning](https://mlsanity.com/paper/2603.16206/) (2026)
- [Free(): Learning to Forget in Malloc-Only Reasoning Models](https://mlsanity.com/paper/2602.08030/) (2026)
- [Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training](https://mlsanity.com/paper/2605.07316/) (2026)
- [SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning](https://mlsanity.com/paper/2605.30832/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable reasoning abilities on complex problems using long Chain-of-Thought (CoT) reasoning. However, they often suffer from overthinking, meaning generating unnecessarily lengthy reasoning steps for simpler problems. This issue may degrade the efficiency of the models and make them difficult to adapt the reasoning depth to the complexity of problems. To address this, we introduce a novel metric Token Entropy Cumulative Average (TECA), which measures the extent of exploration throughout the reasoning process. We further propose a novel reasoning paradigm named "Explore Briefly, Then Decide", with an associated Cumulative Entropy Regulation (CER) mechanism. This paradigm leverages TECA to help the model dynamically determine the optimal point to conclude its thought process and provide a final answer, thus achieving efficient reasoning. Experimental results across diverse mathematical benchmarks show that our approach substantially mitigates overthinking without sacrificing problem solving ability. With our thinking paradigm, the average response length decreases by up to 71% on simpler datasets, demonstrating the effectiveness of our method in creating a more efficient and adaptive reasoning process.