分层推理模型（Hierarchical Reasoning Model，HRM）是一种采用两个以不同频率递归的小型神经网络的新方法。这种受生物启发的方法在数独、迷宫和ARC-AGI等困难谜题任务上优于大语言模型（Large Language models，LLMs），且仅用小模型（27M参数）在小数据（约1000个样本）上训练。HRM在利用小型网络解决困难问题方面极具潜力，但目前尚未被充分理解，且可能并非最优。我们提出微型递归模型（Tiny Recursive Model，TRM），这是一种更简单的递归推理方法，仅使用一个仅含2层的微型网络，泛化能力显著高于HRM。TRM仅含7M参数，在ARC-AGI-1上取得45%的测试准确率，在ARC-AGI-2上取得8%的测试准确率，优于大多数LLMs（如Deepseek R1、o3-mini、Gemini 2.5 Pro），而参数量不到这些模型的0.01%。
英文摘要：
Hierarchical Reasoning Model (HRM) is a novel approach using two small neural networks recursing at different frequencies. This biologically inspired method beats Large Language models (LLMs) on hard puzzle tasks such as Sudoku, Maze, and ARC-AGI while trained with small models (27M parameters) on small data (around 1000 examples). HRM holds great promise for solving hard problems with small networks, but it is not yet well understood and may be suboptimal. We propose Tiny Recursive Model (TRM), a much simpler recursive reasoning approach that achieves significantly higher generalization than HRM, while using a single tiny network with only 2 layers. With only 7M parameters, TRM obtains 45% test-accuracy on ARC-AGI-1 and 8% on ARC-AGI-2, higher than most LLMs (e.g., Deepseek R1, o3-mini, Gemini 2.5 Pro) with less than 0.01% of the parameters.
Towards Efficient Multimodal Unified Reasoning Model via Model Merging
Beijing University of Posts and Telecommunications（北京邮电大学）；Nanyang Technological University（南洋理工大学）；Beijing Key Laboratory of Network System and Network Culture（北京网络系统与网络文化重点实验室）；Key Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism（文化和旅游部交互技术与体验系统重点实验室）；Zhongguancun Academy, Beijing, China（中关村学院，北京，中国）
MedRLM: Recursive Multimodal Health Intelligence for Long-Context Clinical Reasoning, Sensor-Guided Screening, Evidence-Grounded Decision Support, and Community-to-Tertiary Referral Optimization
School of Information, Computer；Communication Technology Sirindhorn International Institute of Technology, Thammasat University Pathum Thani, Thailand 1
The $\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $λ$-Calculus
The School of Interdisciplinary Research（跨学科研究学院）；Indian Institute of Technology (IIT) Delhi（印度理工学院德里分校）；Robert Bosch GmbH, India（德国罗伯特·博世有限公司，印度）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Huawei Noah’s Ark UCL Centre for Artificial Intelligence（华为诺亚方舟大学伦敦人工智能中心）
Mind the Perspective: Let's Reason Recursively for Theory of Mind
School of Computing and Information Systems, The University of Melbourne, Australia（墨尔本大学计算与信息系统学院）；SensiLab, Monash University, Australia（蒙纳士大学SensiLab）
Dynamical Systems Theory Behind a Hierarchical Reasoning Model
Department of Radiophysics, University of Nizhny Novgorod（尼日尼诺夫戈罗德大学无线电物理系）；Huawei Nizhny Novgorod Research Center（华为尼日尼诺夫戈罗德研究中心）；Skolkovo Institute of Science and Technology（斯克洛科夫科学与技术研究院）
TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models
The University of Hong Kong（香港大学）；Peking University（北京大学）；OpenGVLab（开放智能机器研究中心）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding
Chongqing University（重庆大学）；Tianjin University（天津大学）；MAIS, Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院MAIS）；Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore（新加坡科技研究局高性能计算研究所）；Chongqing National Data AI Research Institute, AI Research Lab（重庆国家数据AI研究院，AI研究实验室）
Department of Computer Science, Technical University of Darmstadt（德累斯顿技术大学计算机科学系）；Department of Computer Science, The University of Texas at Dallas（德克萨斯大学达拉斯分校计算机科学系）；Hessian Center for Artificial Intelligence (hessian.ai)（黑森人工智能中心）；German Research Center for AI (DFKI)（德国人工智能研究中心）
Tiny Recursive Models for Solving the J2-Perturbed Lambert Problem
Department of Aerospace Engineering, University of Illinois Urbana-Champaign（航空航天工程系，伊利诺伊大学厄巴纳-香槟分校）；Te Pūnaha Ātea – Space Institute, University of Auckland（太空研究所，奥克兰大学）
