arXiv cs.AI· Jalal Mahmud, Eser Kandogan·· 10 小时前AI 评分26
价值语义层 VSL:让数据库可被 AI 智能体理解
The Value Semantics Layer: Enabling Machine-Understandable Databases for Agentic AI
AI 导读
研究者提出价值语义层(VSL),一种将值语义外化为持久、规划器可见的基础设施架构抽象。VSL 引入可复用的价值语义类型(VST),覆盖分布、关系、过程、定量与策略语义,使规划器能校验分析操作、选择合适算子并引导分析流程。该工作给出 VSL 的动机、形式化、架构与原型实现,并提出面向 AI 原生语义基础设施的研究议程。
正文 · 原文
Abstract:As data systems increasingly support autonomous LLM-powered agents alongside human analysts, they require richer semantic infrastructure bridging analytical concepts and analytical operations. Existing metadata systems expose schemas, catalogs, lineage, and governance information, but provide limited support for representing operational semantics. We propose the Value Semantics Layer (VSL), an architectural abstraction that externalizes value semantics as persistent, planner-visible infrastructure. VSL introduces Value Semantic Types (VSTs), reusable operational semantic assertions capturing distributional, relational, process, quantitative, and policy-grounded semantics. Unlike descriptive metadata, VSTs enable planners to validate analytical operations, select appropriate operators, and guide analytical workflows. We present the motivation, formalization, architecture, and prototype realizations of VSL, and outline a research agenda toward AI-native semantic infrastructure for analytical systems.
| Subjects: | Databases (cs.DB); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.23629 [cs.DB] |
| (or arXiv:2611.23629v1 [cs.DB] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23629 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jalal Mahmud [view email]
[v1]
Tue, 17 Nov 2026 23:41:17 UTC (2,601 KB)
来源:arXiv cs.AI · arxiv.org