发表机构
Politecnico di Milano; ELLIS Institute Finland; Åbo Akademi University; Samsung AI; Delft University of Technology; Stony Brook University; Politecnico di Torino; University of Stuttgart; Graz University of Technology; Lockheed Martin, Advanced Technology Labs; BrainCreators; Vrije Universiteit Amsterdam; University of Amsterdam; University of Edinburgh; UCLA（米兰理工大学; 芬兰ELLIS研究所; 奥博 Akademi 大学; 三星人工智能研究院; 代尔夫特理工大学; 石溪大学; 都灵理工大学; 斯图加特大学; 格拉茨工业大学; 洛克希德·马丁公司先进技术实验室; BrainCreators公司; 阿姆斯特丹自由大学; 阿姆斯特丹大学; 爱丁堡大学; 加利福尼亚大学洛杉矶分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该文提出神经符号AI的RAIL四项原则，可统一分析多类AI系统，助力工程师更科学地设计部署生产级AI，指导整合神经符号方法到下一代AI技术。
AI 中文摘要
集成机器学习与符号推理的神经符号AI系统正迅速受到关注，它们用符号推理算法补充神经网络和大语言模型的数据密集型统计方法，以在高风险领域或真实应用常见的低数据 regime 中运行。本文认为，机器学习与形式推理的神经符号组合并非AI中的小众方法，而是包含诸多已成功的技术，对开发可靠、高效且最终可信赖的系统至关重要，这一视角促使重新审视当前AI系统的设计。我们表明，许多领先AI系统，包括一些传统上不被视为神经符号的系统，都可从神经符号AI设计的四项原则——推理（Reasoning）、保证（Assurances）、接口（Interfacing）与学习（Learning，即RAIL）的视角分析。应用RAIL框架可为看似不同的AI系统提供统一视角，涵盖物理感知机器学习、神经引导搜索（如Google DeepMind的Alpha-*系列）、因果学习及工具增强型大语言模型。重要的是，RAIL原则将使工程师能对生产级AI系统的设计与部署做出更明智、更具原则性的决策。本文介绍RAIL原则，考察其如何应用于AI主要领域，并说明其如何指导从业者将神经符号方法整合到下一代AI技术中。
英文摘要
Neurosymbolic AI systems that integrate machine learning and symbolic reasoning are rapidly gaining attention. They complement the data-intensive statistical approaches of neural networks and language models with symbolic reasoning algorithms to function in high-stakes domains or in low-data regimes that characterize many real-world applications. We argue that the neurosymbolic combination of machine learning and formal reasoning is not a niche approach within AI, but rather includes many already successful techniques that are of crucial importance to the development of reliable, efficient and, ultimately, trustworthy systems. This perspective prompts a re-examination of the design of current AI systems. We show that many leading AI systems, including some that are not traditionally considered as neurosymbolic, can be analysed from the perspective of four principles of neurosymbolic AI design: Reasoning, Assurances, Interfacing and Learning (RAIL). Applying the RAIL framework offers a unified view of seemingly disparate AI systems, ranging from physics-aware machine learning to neuro-guided search (such as Google DeepMind's Alpha-* suite), causal learning and tool-augmented Large Language Models. Importantly, the RAIL principles will enable engineers to make better-informed and more principled decisions about the design and deployment of production-level AI systems. In this article, we introduce the RAIL principles, examine how they can be applied across major areas of AI, and illustrate how they may guide practitioners to integrate neurosymbolic methods into next-generation AI technologies.
