神经符号 AI 的规则语言综述：Datalog、答案集与概率逻辑程序

Rule-Based Languages for Neurosymbolic AI

AI 导读

一篇综述系统梳理了神经符号 AI 中作为符号组件的规则语言，涵盖 Datalog、答案集程序与概率逻辑程序，并沿语义、表达力、神经集成和求值机制四个维度展开分析。作者考察了 50 多个近期系统与应用，比较了数据库与编程语言、机器学习、视觉和机器人四个研究领域的形式化使用情况，并给出将应用场景映射到所需特性的决策矩阵，最后列出开放问题。

正文 · 原文

View PDF HTML (experimental)

Abstract:Logic programming is increasingly used as the symbolic component of neurosymbolic AI systems. We survey the main rule-based languages in this setting, namely Datalog, answer set, and probabilistic logic programs, along four axes: semantics, expressiveness, neural integration, and evaluation mechanism. We analyse over 50 recent systems and applications, comparing formalism usage across four research areas: databases and programming languages, machine learning, vision, and robotics. We provide a decision matrix mapping application scenarios to required features and close by outlining open problems.

Comments:	To appear in the Proceedings of Rules and Reasoning - 10th International Joint Conference, RuleML+RR 2026, Vilnius, Lithuania
Subjects:	Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)
Cite as:	arXiv:2610.07313 [cs.AI]
	(or arXiv:2610.07313v1 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2610.07313 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Stefania Dumbrava [view email]
[v1] Mon, 5 Oct 2026 19:49:56 UTC (52 KB)

来源：arXiv cs.AI · arxiv.org