Buchumschlag

Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Liu, Yongjiang, Li, Haoxi, Ma, Xiaosong, Zhang, Jie, Guo, Song
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
von: Liu, Shuaitong, et al.
Veröffentlicht: (2025)

Mitigating Overthinking in Large Reasoning Models via Difficulty-aware Reinforcement Learning
von: Wan, Qian, et al.
Veröffentlicht: (2026)

TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis
von: Bai, Sikai, et al.
Veröffentlicht: (2026)

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models
von: Shen, Yi, et al.
Veröffentlicht: (2025)

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
von: Fan, Chenrui, et al.
Veröffentlicht: (2025)

Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
von: Guan, Weixin, et al.
Veröffentlicht: (2026)

Mitigating Overthinking through Reasoning Shaping
von: Song, Feifan, et al.
Veröffentlicht: (2025)

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
von: Hassid, Michael, et al.
Veröffentlicht: (2025)

What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity
von: Li, Haoxi, et al.
Veröffentlicht: (2026)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
von: Huang, Yao, et al.
Veröffentlicht: (2025)

Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
von: An, Sohyun, et al.
Veröffentlicht: (2025)

AdaThink-Med: Medical Adaptive Thinking with Uncertainty-Guided Length Calibration
von: Rui, Shaohao, et al.
Veröffentlicht: (2025)

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

When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling
von: Zhou, Shu, et al.
Veröffentlicht: (2026)

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

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

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

Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning
von: Wang, Qianyue, et al.
Veröffentlicht: (2026)

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

From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control
von: Ha, Rui, et al.
Veröffentlicht: (2025)

Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models
von: Yue, Linan, et al.
Veröffentlicht: (2025)

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens
von: Yong, Xixian, et al.
Veröffentlicht: (2025)

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

Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations
von: Song, Zhao, et al.
Veröffentlicht: (2025)

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
von: Xiong, Zidi, et al.
Veröffentlicht: (2025)

Think before Recommendation: Autonomous Reasoning-enhanced Recommender
von: Kong, Xiaoyu, et al.
Veröffentlicht: (2025)

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

Adaptive Dual Reasoner: Large Reasoning Models Can Think Efficiently by Hybrid Reasoning
von: Zhang, Yujian, et al.
Veröffentlicht: (2025)

DeepThink3D: Enhancing Large Language Models with Programmatic Reasoning in Complex 3D Situated Reasoning Tasks
von: Song, Jiayi, et al.
Veröffentlicht: (2025)

LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking
von: Ma, Yukai, et al.
Veröffentlicht: (2025)

Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
von: Ge, Yuyao, et al.
Veröffentlicht: (2025)

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

Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor
von: Ma, Guoxin, et al.
Veröffentlicht: (2026)

AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models
von: Wang, Xiangqi, et al.
Veröffentlicht: (2025)

Think Twice to See More: Iterative Visual Reasoning in Medical VLMs
von: Chen, Kaitao, et al.
Veröffentlicht: (2025)

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

Multi-Persona Thinking for Bias Mitigation in Large Language Models
von: Chen, Yuxing, et al.
Veröffentlicht: (2026)

Thinking on Maps: How Foundation Model Agents Explore, Remember, and Reason Map Environments
von: Wei, Zhiwei, et al.
Veröffentlicht: (2025)

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

AtomThink: Multimodal Slow Thinking with Atomic Step Reasoning
von: Xiang, Kun, et al.
Veröffentlicht: (2024)