Image de couverture de livre

ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jiao, Difan, Wen, Qianfeng, Yang, Blair, Tang, Zhenwei, Anderson, Ashton
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
par: Tang, Zhenwei, et autres
Publié: (2025)

ChessQA: Evaluating Large Language Models for Chess Understanding
par: Wen, Qianfeng, et autres
Publié: (2025)

Grounded Chess Reasoning in Language Models via Master Distillation
par: Tang, Zhenwei, et autres
Publié: (2026)

SPIN: Sparsifying and Integrating Internal Neurons in Large Language Models for Text Classification
par: Jiao, Difan, et autres
Publié: (2023)

Maia-2: A Unified Model for Human-AI Alignment in Chess
par: Tang, Zhenwei, et autres
Publié: (2024)

LLM Safety From Within: Detecting Harmful Content with Internal Representations
par: Jiao, Difan, et autres
Publié: (2026)

Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess
par: Tang, Zhenwei, et autres
Publié: (2025)

Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning
par: Tang, Zhenwei, et autres
Publié: (2026)

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

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

A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models
par: Xie, Chengxing, et autres
Publié: (2024)

Think Twice to See More: Iterative Visual Reasoning in Medical VLMs
par: Chen, Kaitao, et autres
Publié: (2025)

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
par: Cui, Yingqian, et autres
Publié: (2025)

Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
par: An, Sohyun, et autres
Publié: (2025)

Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making
par: Wan, Xu, et autres
Publié: (2025)

Structured Role-Aware Policy Optimization for Multimodal Reasoning
par: Jiang, Bingqing, et autres
Publié: (2026)

SSR: Socratic Self-Refine for Large Language Model Reasoning
par: Shi, Haizhou, et autres
Publié: (2025)

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
par: Liao, Yi, et autres
Publié: (2025)

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
par: Xi, Zhiheng, et autres
Publié: (2023)

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

Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
par: Cheng, Xiaoxue, et autres
Publié: (2025)

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

GPTQT: Quantize Large Language Models Twice to Push the Efficiency
par: Guo, Yipin, et autres
Publié: (2024)

Tandem Training for Language Models
par: West, Robert, et autres
Publié: (2025)

Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents
par: Singhi, Nishad, et autres
Publié: (2026)

Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts
par: Bo, Jessica Y., et autres
Publié: (2026)

Direct Alignment of Language Models via Quality-Aware Self-Refinement
par: Yu, Runsheng, et autres
Publié: (2024)

Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models
par: Du, Chengyu, et autres
Publié: (2024)

Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models
par: Elenjical, Abraham Paul, et autres
Publié: (2026)

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

Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agents
par: Jaiswal, Raj, et autres
Publié: (2024)

A Convergence Analysis of Adaptive Optimizers under Floating-point Quantization
par: Tang, Xuan, et autres
Publié: (2025)

Thinking About Thinking: SAGE-nano's Inverse Reasoning for Self-Aware Language Models
par: Jha, Basab, et autres
Publié: (2025)

DeepThink3D: Enhancing Large Language Models with Programmatic Reasoning in Complex 3D Situated Reasoning Tasks
par: Song, Jiayi, et autres
Publié: (2025)

AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models
par: Wang, Xiangqi, et autres
Publié: (2025)

Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement
par: Zhang, Yunjian, et autres
Publié: (2026)

InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models
par: Yan, Yuchen, et autres
Publié: (2025)

Efficient Post-Training Refinement of Latent Reasoning in Large Language Models
par: Wang, Xinyuan, et autres
Publié: (2025)

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
par: Xiong, Zidi, et autres
Publié: (2025)

Modeling Hierarchical Thinking in Large Reasoning Models
par: Shahariar, G M, et autres
Publié: (2025)