Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Semantic Modeling for World-Centered Architectures

Andrei Mantsivoda, Darya Gavrilina

Abstract

We introduce world-centered multi-agent systems (WMAS) as an alternative to traditional agent-centered architectures, arguing that structured domains such as enterprises and institutional systems require a shared, explicit world representation to ensure semantic consistency, explainability, and long-term stability. We classify worlds along dimensions including ontological explicitness, normativity, etc. In WMAS, learning and coordination operate over a shared world model rather than isolated agent-local representations, enabling global consistency and verifiable system behavior. We propose semantic models as a mathematical formalism for representing such worlds. Finally, we present the Ontobox platform as a realization of WMAS.

Semantic Modeling for World-Centered Architectures

Abstract

We introduce world-centered multi-agent systems (WMAS) as an alternative to traditional agent-centered architectures, arguing that structured domains such as enterprises and institutional systems require a shared, explicit world representation to ensure semantic consistency, explainability, and long-term stability. We classify worlds along dimensions including ontological explicitness, normativity, etc. In WMAS, learning and coordination operate over a shared world model rather than isolated agent-local representations, enabling global consistency and verifiable system behavior. We propose semantic models as a mathematical formalism for representing such worlds. Finally, we present the Ontobox platform as a realization of WMAS.

Paper Structure

This paper contains 38 sections, 1 equation, 1 figure.

Table of Contents

  1. Introduction
  2. World-Centered Architectures for Multi-Agent Systems
  3. From Agent-Centered to World-Centered Thinking
  4. What Is a "World" in a Multi-Agent System?
  5. Fundamental Dimensions of Worlds
  6. Dimension A: Ontological Explicitness.
  7. Dimension B: Structural Stability.
  8. Dimension C: Normativity (Rule-Governedness).
  9. Dimension D: Observability and State Accessibility.
  10. Dimension E: Semantic Ambition (Open-Endedness).
  11. Dimension F: Perception-to-Deliberation Ratio.
  12. A Classification of World Types
  13. Type I: Institutional / Enterprise Worlds (Ideal Case).
  14. Type II: Formal Synthetic Worlds (Highly Suitable).
  15. Type III: Hybrid Cyber-Physical Worlds (Partially Suitable).
  16. ...and 23 more sections

Figures (1)

  • Figure 1: A Semantic Model for the World-Centered Architecture

Theorems & Definitions (2)

  • Definition 1: World
  • Definition 2: Applicability of World-Centered MAS