跳到正文
arXiv cs.AI· Jalal Mahmud, Eser Kandogan·· 1 小时前AI 评分34

价值语义层(VSL):让数据库可被 Agentic AI 理解的语义基础设施

The Value Semantics Layer: Enabling Machine-Understandable Databases for Agentic AI

AI 导读

arXiv 论文提出价值语义层(VSL),一种将价值语义外化为持久、规划器可见的基础设施的架构抽象。VSL 引入可复用的价值语义类型(VST),涵盖分布、关系、过程、量化与策略语义,使 LLM 智能体规划器能校验分析操作、选择算子并引导分析流程,区别于仅描述性的元数据系统。论文还给出形式化、架构与原型实现,并展望面向 AI 原生语义基础设施的研究议程。

正文 · 原文

View PDF HTML (experimental)

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