The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognised as one of the key challenges of modern AI. Recent years have seen large number of publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature is highly diverse and mostly empirical, and is lacking a unifying view of the large variety of these hybrid systems. In this paper we analyse a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems. We are able to describe the architecture of a very large number of hybrid systems by composing only a small set of elementary patterns as building blocks.
The main contributions of this paper are: 1) a taxonomically organised vocabulary to describe both processes and data structures used in hybrid systems; 2) a set of 15+ design patterns for hybrid AI systems, organised in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems. Our patterns reveal similarities between systems that were not recognised until now. Finally, our design patterns extend and refine Kautz' earlier attempt at categorising neuro-symbolic architectures.
Radiology's Last Exam (RadLE): Benchmarking Frontier Multimodal AI Against Human Experts and a Taxonomy of Visual Reasoning Errors in Radiology
Centre for Responsible Autonomous Systems in Healthcare (CRASH) Lab, Koita Centre for Digital Health（负责任的自主医疗系统中心（CRASH）实验室、Koita数字健康中心）；Ashoka University（阿什oka大学）；Independent Researcher（独立研究者）；Koita Centre for Digital Health（Koita数字健康中心）
Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning
UNC Chapel Hill（北卡罗来纳大学教堂山分校）
多跳QA需要一个模型来连接分散在长上下文中的多个证据来回答问题。最近提出的HotpotQA（Yang等人，2018）数据集由体现四种不同的多跳推理范例（两个桥接实体设置、检查多个属性和比较两个实体）的问题组成，使得单个神经网络处理所有四个问题具有挑战性。在这项工作中，我们提出了一个可解释的，基于神经网络的自组装神经模块网络（Hu et al.，2017年，2018年）的多跳推理，在那里我们设计了四个新的模块（查找，重新定位，比较，NoOp）来执行独特类型的语言推理。基于一个问题，我们的布局控制器RNN动态地推断一系列推理模块来构建整个网络。从经验上讲，我们表明，我们的动态，多跳模块化网络实现了显着的改进，静态，单跳基线（定期和对抗性评估）。我们通过三个分析进一步证明了我们的模型的可解释性。首先，控制器可以将多跳问题软分解为多个单跳子问题，以促进主网络的组合推理行为。其次，控制器可以预测符合人类专家设计的布局的布局。最后，中间模块可以通过处理来自控制器的子问题来推断连接两个远距离定位的支持事实的实体。
Superficial Reflection or Genuine Thought? A Fine-Grained Cognitive Analysis of Large Reasoning Models
University College London London United Kingdom；The Hong Kong University of Science；Tianjin University Tianjin China；Southern University of Science；University of Bristol Bristol United Kingdom；University College London；AI Lab, the Yangtze River Delta, China；Tianjin University；University of Bristol
When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance
School of Law, China University of Political Science and Law（中国政法大学法学院）；Zhejiang University of Finance and Economics Dongfang College（浙江财经大学东洋学院）；School of Information Management for Law, China University of Political Science and Law（中国政法大学信息管理法学院）；Department of Artificial Intelligence, Chung-Ang University（成均馆大学人工智能系）；Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University（香港理工大学数据科学与人工智能系）
Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents
Clemson University（克莱姆森大学）；University of Manitoba（曼尼托巴大学）；Northwestern University（西北大学）；American University of Sharjah（沙迦美国大学）；Michigan State University（密歇根州立大学）；Medical University of Gdańsk（格但斯克医科大学）
Cognitive bias in LLM reasoning compromises interpretation of clinical oncology notes
Mayo Clinic College of Medicine and Science（梅奥诊所医学与科学学院）；School of Computing and AI, Arizona State University（亚利桑那州立大学计算与人工智能学院）；Mayo Clinic Comprehensive Cancer Center（梅奥诊所综合癌症中心）；Department of Radiation Oncology, Mayo Clinic（梅奥诊所放射肿瘤科）；Department of Oncology, Mayo Clinic（梅奥诊所肿瘤科）；Department of Artificial Intelligence and Informatics, Mayo Clinic（梅奥诊所人工智能与信息学系）；Dana-Farber Cancer Institute, Harvard Medical School（哈佛医学院丹娜-法伯癌症研究所）
Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations
Pengcheng Laboratory（鹏城实验室）；International Digital Economy Academy（国际数字经济学院）；School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；School of AI for Science, Peking University（北京大学科学人工智能学院）；Yale University（耶鲁大学）
A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs
College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算机与数据科学学院）；Institute for Infocomm Research, A*STAR, Singapore（资讯通信研究院）；School of Computer Science and Engineering, Beihang University, China（北京航空航天大学计算机科学与工程学院）
UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks
Lincoln North Star High School（林肯北星高中）；The Charter School of Wilmington（威尔明顿 charter 学校）；Greenwich High School（格林威治高中）；Santa Susana High School（圣塔苏娜高中）；UC Berkeley（伯克利大学）
ChainReaction: Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answering
Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore（新加坡高性能计算研究所，科技研究局）；Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore（科技研究局前沿人工智能研究中心，新加坡）；College of Computing and Data Science, Nanyang Technological University, Singapore（新加坡南洋理工大学计算与数据科学学院）
LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
Beijing Jiaotong University（北京交通大学）；Lancaster University（兰卡斯特大学）；Max Planck Institute for Informatics, Saarland Informatics Campus（马克斯·普朗克研究所（信息学）萨尔兰州信息学校区）；University of Electronic Science and Technology of China（电子科技大学）
