cs.DBNov 17, 2026

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

Authors: Jalal Mahmud, Eser Kandogan

Organizations: Megagon Labs, Mountain View, California, USA

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.

Figures & tables

Explore similar work

CardsList
  1. LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents

    Jun 29, 2026Yogeswar Reddy ThotaComputer-Use AgentsGUI Automation

  2. Do Agents Need Semantic Metadata? A Comparative Study in Agentic Data Retrieval

    May 27, 2026Shiyu Chen, Tarfah Alrashed, Alon Halevy +1LLM Agent EvaluationAgentic Retrieval