Semantic Modeling for World-Centered Architectures

TL;DR

This paper proposes world-centered multi-agent systems (WMAS) with shared, explicit world models to improve consistency, explainability, and stability in complex domains, exemplified by the Ontobox platform.

Contribution

It introduces a formal semantic modeling framework for WMAS and presents the Ontobox platform as a practical implementation.

Findings

Shared world models enable global consistency in multi-agent systems.

Semantic formalism facilitates verifiable and explainable system behavior.

Ontobox demonstrates the feasibility of WMAS in real-world applications.

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.