Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xia, Wei, Wang, Haoqing, Deng, Zhi-Hong, Tang, Yehui
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks
by: Long, Xiang, et al.
Published: (2026)

Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration
by: Deng, Wenhao, et al.
Published: (2025)

How Likely Do LLMs with CoT Mimic Human Reasoning?
by: Bao, Guangsheng, et al.
Published: (2024)

The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
by: Català, Mar Gonzàlez I, et al.
Published: (2026)

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
by: Yue, Murong, et al.
Published: (2024)

Do LLMs Encode Functional Importance of Reasoning Tokens?
by: Singh, Janvijay, et al.
Published: (2026)

Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search
by: Cui, Yingqian, et al.
Published: (2025)

ABench-Physics: Benchmarking Physical Reasoning in LLMs via High-Difficulty and Dynamic Physics Problems
by: Zhang, Yiming, et al.
Published: (2025)

When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
by: McGovern, Hope, et al.
Published: (2026)

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
by: Xu, Hongling, et al.
Published: (2025)

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
by: Cui, Ganqu, et al.
Published: (2025)

When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation
by: Faisal, Faizan
Published: (2026)

When Less is Enough: Efficient Inference via Collaborative Reasoning
by: Chen, Yilei, et al.
Published: (2026)

When Attention Sink Emerges in Language Models: An Empirical View
by: Gu, Xiangming, et al.
Published: (2024)

MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs
by: Zhao, Guojiang, et al.
Published: (2025)

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
by: Wang, Kai, et al.
Published: (2025)

Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
by: Jin, Renren, et al.
Published: (2025)

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning
by: Singhi, Nishad, et al.
Published: (2025)

Lost in Transmission: When and Why LLMs Fail to Reason Globally
by: Schnabel, Tobias, et al.
Published: (2025)

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
by: Wang, Qibin, et al.
Published: (2025)

A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
by: Hong, Guan Zhe, et al.
Published: (2024)

When More is Less: Understanding Chain-of-Thought Length in LLMs
by: Wu, Yuyang, et al.
Published: (2025)

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
by: DeepSeek-AI, et al.
Published: (2025)

Understanding Reasoning in Chain-of-Thought from the Hopfieldian View
by: Hu, Lijie, et al.
Published: (2024)

Retrieval Augmented Question Answering: When Should LLMs Admit Ignorance?
by: Wang, Dingmin, et al.
Published: (2025)

Rethinking Entropy Regularization in Large Reasoning Models
by: Jiang, Yuxian, et al.
Published: (2025)

Dynamic Experts Search: Enhancing Reasoning in Mixture-of-Experts LLMs at Test Time
by: Han, Yixuan, et al.
Published: (2025)

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning
by: Yu, Erxin, et al.
Published: (2025)

When Answers Stray from Questions: Hallucination Detection via Question-Answer Orthogonal Decomposition
by: Yao, Siyang, et al.
Published: (2026)

Do Multilingual LLMs Think In English?
by: Schut, Lisa, et al.
Published: (2025)

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
by: Tang, Yao, et al.
Published: (2026)

Weak-to-Strong Elicitation via Mismatched Wrong Drafts
by: Deng, Wei
Published: (2026)

MathScale: Scaling Instruction Tuning for Mathematical Reasoning
by: Tang, Zhengyang, et al.
Published: (2024)

SDA: Steering-Driven Distribution Alignment for Open LLMs without Fine-Tuning
by: Xia, Wei, et al.
Published: (2025)

Small LLMs Do Not Learn a Generalizable Theory of Mind via Reinforcement Learning
by: Sarangi, Sneheel, et al.
Published: (2025)

Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing
by: Le, Qi, et al.
Published: (2025)

Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
by: Wang, Chenyang, et al.
Published: (2025)

Where Do Reasoning Models Refuse?
by: Yamaguchi, Kureha, et al.
Published: (2025)

Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR
by: Gu, Hengrui, et al.
Published: (2026)

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations
by: Jaipersaud, Brandon, et al.
Published: (2025)