Cover Image

Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Han, Jinyi, Huang, Ying, Liao, Ying, Jiang, Zishang, Lu, Xikun, Zhao, Haiquan, Wang, Xinyi, Zhou, Guanghao, Jiang, Sihang, Liang, Jiaqing, Zhou, Weikang, Sun, Zeye, Yu, Fei, Xiao, Yanghua
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

A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models
by: Han, Jinyi, et al.
Published: (2025)

Structured Reasoning for Large Language Models
by: Han, Jinyi, et al.
Published: (2026)

Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation
by: He, Qianxi, et al.
Published: (2025)

HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness
by: Wang, Xinyi, et al.
Published: (2025)

Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs
by: Jiang, Zishang, et al.
Published: (2025)

Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following
by: Ren, Qingyu, et al.
Published: (2025)

Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models
by: Ren, Qingyu, et al.
Published: (2025)

Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following
by: Zeng, Jie, et al.
Published: (2025)

Enhancing Quantitative Reasoning Skills of Large Language Models through Dimension Perception
by: Huang, Yuncheng, et al.
Published: (2023)

GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
by: Liang, Jiaqing, et al.
Published: (2026)

Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
by: Sun, Renliang, et al.
Published: (2025)

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
by: Sui, Yang, et al.
Published: (2025)

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

LogReasoner: Empowering LLMs with Expert-like Coarse-to-Fine Reasoning for Automated Log Analysis
by: Ma, Lipeng, et al.
Published: (2025)

Quite Good, but Not Enough: Nationality Bias in Large Language Models -- A Case Study of ChatGPT
by: Zhu, Shucheng, et al.
Published: (2024)

Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models
by: Du, Chengyu, et al.
Published: (2024)

Stop Overthinking: Unlocking Efficient Listwise Reranking with Minimal Reasoning
by: Liu, Danyang, et al.
Published: (2026)

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
by: Wei, Zihao, et al.
Published: (2025)

Learning to Stop Overthinking at Test Time
by: Bao, Hieu Tran, et al.
Published: (2025)

ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model
by: Chen, Xiaoshu, et al.
Published: (2026)

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following
by: Ren, Qingyu, et al.
Published: (2025)

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

Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding
by: Li, Yanda, et al.
Published: (2024)

Do Large Language Models Truly Understand Cross-cultural Differences?
by: Guo, Shiwei, et al.
Published: (2025)

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

LUK: Empowering Log Understanding with Expert Knowledge from Large Language Models
by: Ma, Lipeng, et al.
Published: (2024)

Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
by: Xia, Sirui, et al.
Published: (2024)

Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster
by: Chen, Xiao, et al.
Published: (2025)

AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model
by: Ma, Lipeng, et al.
Published: (2025)

Batch Prompting Suppresses Overthinking Reasoning Under Constraint: How Batch Prompting Suppresses Overthinking in Reasoning Models
by: Srivastava, Saurabh, et al.
Published: (2025)

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit
by: Yi, Biao, et al.
Published: (2025)

LsrIF: Enhancing Logic-Structured Instruction Following of Large Language Models
by: Ren, Qingyu, et al.
Published: (2026)

Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling
by: Jiang, Shuyang, et al.
Published: (2025)

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
by: Pu, Xiao, et al.
Published: (2025)

Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
by: Diao, Xingjian, et al.
Published: (2026)

ConcEPT: Concept-Enhanced Pre-Training for Language Models
by: Wang, Xintao, et al.
Published: (2024)

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
by: Zhang, Mohan, et al.
Published: (2025)

SEIF: Self-Evolving Reinforcement Learning for Instruction Following
by: Ren, Qingyu, et al.
Published: (2026)

SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
by: Li, Guanghao, et al.
Published: (2025)

Domain Generalization via Discrete Codebook Learning
by: Long, Shaocong, et al.
Published: (2025)