Cover Image

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Rongzhi, Liu, Yi, Sun, Zequn, Wang, Yiwei, Hu, Wei
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models
by: Liu, Yi, et al.
Published: (2025)

A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning
by: Cui, Yuanning, et al.
Published: (2024)

AdaptThink: Reasoning Models Can Learn When to Think
by: Zhang, Jiajie, et al.
Published: (2025)

Reasoning Models Can Be Effective Without Thinking
by: Ma, Wenjie, et al.
Published: (2025)

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
by: Zhang, Xiaoyun, et al.
Published: (2025)

Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion
by: Liu, Yang, et al.
Published: (2024)

Can Large Language Models do Analytical Reasoning?
by: Hu, Yebowen, et al.
Published: (2024)

Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective
by: Sun, Zhongxiang, et al.
Published: (2025)

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
by: Zhu, Zihao, et al.
Published: (2025)

Modeling Hierarchical Thinking in Large Reasoning Models
by: Shahariar, G M, et al.
Published: (2025)

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
by: Zhu, Jason, et al.
Published: (2025)

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning
by: Chen, Haoyang, et al.
Published: (2026)

Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering
by: Zhu, Rongzhi, et al.
Published: (2025)

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model
by: Wan, Xu, et al.
Published: (2025)

To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks
by: Gong, Nanxu, et al.
Published: (2026)

Exploring the System 1 Thinking Capability of Large Reasoning Models
by: Zhang, Wenyuan, et al.
Published: (2025)

LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models
by: Hao, Shibo, et al.
Published: (2024)

Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
by: Guo, Zhenyuan, et al.
Published: (2026)

LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
by: Wang, Jingyuan, et al.
Published: (2025)

Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models
by: Liu, Yule, et al.
Published: (2025)

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

Controlling Thinking Speed in Reasoning Models
by: Lin, Zhengkai, et al.
Published: (2025)

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
by: Lu, Yi, et al.
Published: (2025)

Cognitive Decision Routing in Large Language Models: When to Think Fast, When to Think Slow
by: Du, Y., et al.
Published: (2025)

Certainty-Guided Reasoning in Large Language Models: A Dynamic Thinking Budget Approach
by: Nogueira, João Paulo, et al.
Published: (2025)

Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models
by: Elenjical, Abraham Paul, et al.
Published: (2026)

When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
by: Mao, Yingzhi, et al.
Published: (2025)

ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents
by: Zhang, Xiaohui, et al.
Published: (2026)

Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models
by: Yu, Longxuan, et al.
Published: (2026)

TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance
by: Wang, Haorui, et al.
Published: (2024)

Break the Chain: Large Language Models Can be Shortcut Reasoners
by: Ding, Mengru, et al.
Published: (2024)

ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization
by: Li, Sunzhu, et al.
Published: (2025)

Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time
by: Yang, Wang, et al.
Published: (2025)

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
by: Chen, Xi, et al.
Published: (2025)

Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
by: Yan, Yibo, et al.
Published: (2025)

Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
by: Cheng, Xiaoxue, et al.
Published: (2025)

InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models
by: Yan, Yuchen, et al.
Published: (2025)

Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model
by: Ding, Bowen, et al.
Published: (2025)

Large Language Models Can Self-Improve in Long-context Reasoning
by: Li, Siheng, et al.
Published: (2024)

Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought
by: Lee, Jooyoung, et al.
Published: (2024)