Image de couverture de livre

Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tian, Xiaoyu, Zhao, Sitong, Wang, Haotian, Chen, Shuaiting, Ji, Yunjie, Peng, Yiping, Zhao, Han, Li, Xiangang
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale
par: Ji, Yunjie, et autres
Publié: (2025)

DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training
par: Tian, Xiaoyu, et autres
Publié: (2025)

Leveraging Reasoning Model Answers to Enhance Non-Reasoning Model Capability
par: Wang, Haotian, et autres
Publié: (2025)

How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study
par: Ji, Yunjie, et autres
Publié: (2025)

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study
par: Tian, Xiaoyu, et autres
Publié: (2025)

1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training
par: Zhao, Han, et autres
Publié: (2025)

Not All Correct Answers Are Equal: Why Your Distillation Source Matters
par: Tian, Xiaoyu, et autres
Publié: (2025)

Think Twice: Branch-and-Rethink Reasoning Reward Model
par: Jiao, Yizhu, et autres
Publié: (2025)

Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning
par: He, Jiashu, et autres
Publié: (2026)

Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens
par: Chen, Wei-Lin, et autres
Publié: (2026)

Don't Think Twice! Over-Reasoning Impairs Confidence Calibration
par: Lacombe, Romain, et autres
Publié: (2025)

Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning
par: Yang, Wenkai, et autres
Publié: (2025)

Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning
par: Zhao, Haodong, et autres
Publié: (2025)

MeTHanol: Modularized Thinking Language Models with Intermediate Layer Thinking, Decoding and Bootstrapping Reasoning
par: Xi, Ningyuan, et autres
Publié: (2024)

Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection
par: Phan, Hoang, et autres
Publié: (2025)

To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks
par: Gong, Nanxu, et autres
Publié: (2026)

Think Twice Before You Judge: Mixture of Dual Reasoning Experts for Multimodal Sarcasm Detection
par: Jana, Soumyadeep, et autres
Publié: (2025)

ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization
par: Li, Sunzhu, et autres
Publié: (2025)

MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoning
par: Chen, Hongwei, et autres
Publié: (2025)

Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
par: Tan, Wenhui, et autres
Publié: (2025)

Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems
par: Tang, Fei, et autres
Publié: (2025)

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
par: Zhang, Xiaoyun, et autres
Publié: (2025)

Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation
par: Qian, Yushan, et autres
Publié: (2023)

Do not be greedy, Think Twice: Sampling and Selection for Document-level Information Extraction
par: Zubillaga, Mikel, et autres
Publié: (2026)

Could Thinking Multilingually Empower LLM Reasoning?
par: Gao, Changjiang, et autres
Publié: (2025)

Efficient Reasoning with Balanced Thinking
par: Li, Yulin, et autres
Publié: (2026)

Steering LLM Thinking with Budget Guidance
par: Li, Junyan, et autres
Publié: (2025)

Thinking with Visual Abstract: Enhancing Multimodal Reasoning via Visual Abstraction
par: Liu, Dairu, et autres
Publié: (2025)

ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute
par: Wen, Hao, et autres
Publié: (2025)

Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning
par: Tang, Lexiang, et autres
Publié: (2026)

Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
par: Cheng, Xiaoxue, et autres
Publié: (2025)

"Well, Keep Thinking": Enhancing LLM Reasoning with Adaptive Injection Decoding
par: Jin, Hyunbin, et autres
Publié: (2025)

Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models
par: Mikula, Lukáš, et autres
Publié: (2023)

Thinking Long, but Short: Stable Sequential Test-Time Scaling for Large Reasoning Models
par: Metel, Michael R., et autres
Publié: (2026)

Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoning
par: Yu, Kun-Yang, et autres
Publié: (2026)

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
par: Zhang, Junyu, et autres
Publié: (2025)

Learning a Continue-Thinking Token for Enhanced Test-Time Scaling
par: Ringel, Liran, et autres
Publié: (2025)

Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection
par: Li, Moxin, et autres
Publié: (2024)

Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning
par: Li, Chengzu, et autres
Publié: (2026)

Thinking with Knowledge Graphs: Enhancing LLM Reasoning Through Structured Data
par: Wu, Xue, et autres
Publié: (2024)