Reasoning language models have shown an uncanny ability to improve performance at test-time by ``thinking longer''-that is, by generating longer chain-of-thought sequences and hence using more compute. However, the length of their chain-of-thought reasoning is not controllable, making it impossible to allocate test-time compute to achieve a desired level of performance. We introduce Length Controlled Policy Optimization (LCPO), a simple reinforcement learning method that optimizes for accuracy and adherence to user-specified length constraints. We use LCPO to train L1, a reasoning language model that produces outputs satisfying a length constraint given in its prompt. L1's length control allows for smoothly trading off computational cost and accuracy on a wide range of tasks, and outperforms the state-of-the-art S1 method for length control. Furthermore, we uncover an unexpected short chain-of-thought capability in models trained with LCPO. Specifically, using LCPO we derive Short Reasoning Models (SRMs), that exhibit similar reasoning patterns as full-length reasoning models, but can generate CoT lengths comparable to non-reasoning models. They demonstrate significant performance gains, for instance, our 1.5B L1 model surpasses GPT-4o at equal reasoning lengths. Overall, LCPO enables precise control over reasoning length, allowing for fine-grained allocation of test-time compute and accuracy. We release code and models at https://www.cmu-l3.github.io/l1
ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning
Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of British Columbia（不列颠哥伦比亚大学）；University College London（伦敦大学学院）
School of Computing, National University of Singapore, Singapore（新加坡国立大学计算机学院）；Department of Statistics, University of Oxford, United Kingdom（英国牛津大学统计系）；School of Intelligence Science（智能科学学院）；Technology, Nanjing University, China（技术学院，南京大学，中国）
Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey
University of Oklahoma（俄克拉荷马大学）；Stanford University（斯坦福大学）；School of Electrical and Computer Engineering, Oklahoma State University（电气与计算机工程学院，俄克拉荷马州立大学）；University of Glasgow（格拉斯哥大学）
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Tencent AI Lab Seattle（腾讯人工智能实验室西雅图）；University of Maryland, College Park（马里兰大学帕克分校）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；City University of Hong Kong（香港城市大学）；Washington University in St. Louis（圣路易斯华盛顿大学）
C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis
School of Computer Science, South China Normal University（华南师范大学计算机科学学院）；School of Electronic and Information Engineering, South China University of Technology（华南理工大学电子与信息工程学院）
TACLer: Tailored Curriculum Reinforcement Learning for Efficient Reasoning
Department of XXX, University of YYY, Location, Country（XXX系，YYY大学，地点，国家）；School of ZZZ, Institute of WWW, Location, Country（ZZZ学院，WWW研究所，地点，国家）；Center for Language and Cognition (CLCG), University of Groningen, The Netherlands（语言与认知中心（CLCG），格罗宁根大学，荷兰）
AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering
Computer Science, Fudan University（复旦大学计算机科学系）；Institute of Modern Languages and Linguistics, Fudan University（复旦大学现代语言与语言学研究院）；Shanghai Innovation Institute（上海创新研究院）；Soochow University（苏州大学）
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
The Swiss AI Lab（瑞士人工智能实验室）；Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA)（达勒·莫勒人工智能研究所（IDSIA））；Università della Svizzera italiana (USI)（瑞士意大利语区大学（USI））；Scuola universitaria professionale della Svizzera italiana (SUPSI)（瑞士意大利语区应用科学与艺术大学（SUPSI））
TKG-Thinker: Towards Dynamic Reasoning over Temporal Knowledge Graphs via Agentic Reinforcement Learning
School of Computer Science, Wuhan University（武汉大学计算机学院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）；Department of Computer Science, National University of Singapore（新加坡国立大学计算机科学系）；Ant Group（蚂蚁集团）
Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiaotong University（上海交通大学）；Zhejiang University（浙江大学）；University of Chinese Academy of Sciences（中国科学院大学）
The Challenges of Using Reinforcement Learning for Controlling Industrial Energy Systems
Institute for Production Management, Technology and Machine Tools (PTW), Technical University of Darmstadt（技术大学达姆施塔特生产管理、技术与机床研究所）；DFKI GmbH, SAIROL（DFKI GmbH，SAIROL）；Department of Computer Science, Technical University of Darmstadt（技术大学达姆施塔特计算机科学系）；Hessian.ai, Technical University of Darmstadt（黑森人工智能公司，技术大学达姆施塔特）
