We challenge the prevailing assumption that complex reasoning in large language models (LLMs) necessitates massive training data. We demonstrate that sophisticated mathematical reasoning can emerge with only a few examples. Specifically, through simple supervised fine-tuning, our model, LIMO, achieves 63.3\% accuracy on AIME24 and 95.6\% on MATH500, surpassing previous fine-tuned models (6.5\% on AIME24, 59.2\% on MATH500) while using only 1\% of the training data required by prior approaches. Furthermore, LIMO exhibits strong out-of-distribution generalization, achieving a 45.8\% absolute improvement across diverse benchmarks, outperforming models trained on 100x more data. Synthesizing these findings, we propose the Less-Is-More Reasoning Hypothesis (LIMO Hypothesis): In foundation models where domain knowledge has been comprehensively encoded during pre-training, sophisticated reasoning can emerge through minimal but strategically designed demonstrations of cognitive processes. This hypothesis suggests that the threshold for eliciting complex reasoning is not dictated by task complexity but rather by two key factors: (1) the completeness of the model's pre-trained knowledge base and (2) the effectiveness of post-training examples in serving as "cognitive templates" that guide reasoning.
OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Models
Mahidol University（玛希隆大学）；iApp Technology Co., Ltd.（iApp科技有限公司）；Intelligent Informatics and Service Innovation Research Center（智能信息与服务创新研究中心）；Artificial Intelligence Entrepreneur Association of Thailand (AIEAT)（泰国人工智能企业家协会（AIEAT））
MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis
Huawei Large Model Data Technology Lab（华为大模型数据技术实验室）；Tsinghua University（清华大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Kyoto University（京都大学）
Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；Key Laboratory of Symbolic Computation and Knowledge Engineering, MoE, Jilin University（吉林大学符号计算与知识工程重点实验室）；Tongyi Lab, Alibaba Group（阿里集团通义实验室）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）
Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models
LARG, Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology（大型语言模型研究组，社会计算与交互机器人研究中心，哈尔滨工业大学）；School of Computer Science and Engineering, Central South University（计算机科学与工程学院，中南大学）
Acting Less is Reasoning More! Teaching Model to Act Efficiently
The Chinese University of Hong Kong（香港中文大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴娜-香槟分校）；Princeton University（普林斯顿大学）；Sun Yat-sen University（中山大学）；Hong Kong University of Science and Technology（香港科学理工大学）
Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Central South University（中南大学）；Text Computing and Cognitive Intelligence Ministry of Education Engineering Research Center, Guizhou University（贵州省教育厅Text Computing and Cognitive Intelligence工程研究中心，贵州大学）；University of Science and Technology Beijing（北京科技大学）；Shanghai Jiao Tong University（上海交通大学）；Shanghai Innovation Institute（上海创新研究院）
Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training
National University of Singapore（新加坡国立大学）；Nanjing University（南京大学）；Fudan University（复旦大学）；The University of Sydney（悉尼大学）；The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）
When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
Harbin Institute of Technology（哈尔滨工业大学）；Singapore Management University（新加坡管理学院）；Monash University（墨尔本大学）；Singapore University of Technology and Design（新加坡科技设计大学）；National University of Singapore（国立新加坡大学）
Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
AI Safety of Chinese Academy of Sciences, Institute of Computing Technology, CAS（中国科学院人工智能安全研究院，中国科学院计算技术研究所）；University of California, Merced（加州大学默塞德分校）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；University of Chinese Academy of Sciences（中国科学院大学）
Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；School of Information, Renmin University of China（中国人民大学信息学院）；China Mobile Information Technology Center（中国移动信息技术中心）
Beijing University of Posts and Telecommunications（北京邮电大学）；School of Artificial Intelligence and Data Science, University of International Business and Economics（国际经济贸易大学人工智能与数据科学学院）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学北京校区人工智能学院）
