arXiv Machine Learning June 2, 2026 By Ting Xu, Xu He, Yupu Lu, Jiankai Sun, Dong Li, Wai Lam, Jianye Hao

Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning

Read the original on arXiv Machine Learning →

arXiv:2606. 02020v1 Announce Type: cross Abstract: This paper investigates the entropy dynamics of Chain-of-Thought (CoT) and uncovers a consistent two-phase structure: an Uncertainty Region of exploration transitioning sharply to a Confidence Region of convergence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 17

Early Stopping for Large Reasoning Models via Confidence Dynamics

arXiv:2604. 04930v2 Announce Type: replace-cross Abstract: Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade performance due to overthinking.

By Parsa Hosseini, Sumit Nawathe, Mahdi Salmani, Meisam Razaviyayn, Soheil Feizi

benchmarks

arXiv AI

Jun 11

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

arXiv:2606. 11211v1 Announce Type: cross Abstract: The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment.

By Prakul Sunil Hiremath, Harshit R. Hiremath

llms

arXiv AI

Jun 16

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions

arXiv:2605. 22873v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial?

By Wei Xia, Haoqing Wang, Zhi-Hong Deng, Yehui Tang

llms benchmarks

arXiv Machine Learning

Sep 1

ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning

arXiv:2608.28771v1 Announce Type: new Abstract: Large reasoning models achieve strong performance on complex tasks by generating extended chain-of-thought (CoT) traces via reinforcement learning with...

By Xin Jiang, Minhao Wang, Wen Wu, Zhentao Xie, Shangheng Du, Jinxin Shi, Jiabao Zhao

llms reinforcement-learning

arXiv Computation and Language

Sep 10

Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models

The paper evaluates entropy-based pruning for compressing Chain-of-Thought (CoT) reasoning in large models. Across multiple models and tasks, low- and high-entropy step selection shows no advantage over random pruning, and low-entropy token retention only helps on mathematical benchmarks due to the low entropy of numeric tokens. Patching a few CoT tokens with their original activations restores near-perfect performance, indicating that task information is distributed throughout the entire reasoning chain rather than concentrated in a small set of tokens.

By Sara Candussio, Daniel Scalena, Luca Bortolussi, Elisabetta Fersini, Malvina Nissim, Gabriele Sarti

efficiency benchmarks

arXiv Machine Learning

Aug 11

Consilience for Verifier-Free Test-Time Scaling

arXiv:2608. 09898v1 Announce Type: cross Abstract: Test-time scaling often uses an external verifier, such as compilers and test cases in coding or trained value functions in robotics applications, to obtain high-quality rollouts.

By Lecheng Kong, Like Hui, Haitao Mao, Jun Huan

llms robotics

One email a morning, machine-written

Related stories

Early Stopping for Large Reasoning Models via Confidence Dynamics

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions

ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning

Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models

Consilience for Verifier-Free Test-Time Scaling