A Framework for Ontology-Driven Multiagent System Generation
Bogdan Okreša Đurić, Carlos Carrascosa · 2025
This paper presents a novel framework for developing multiagent systems using ontology-based modelling consisting of an ontology and an executable module to translate ontology to implementation templates. It systematically maps concepts and relationships to agent roles, behaviours, and interactions by capturing domain knowledge in an ontology. Furthermore, it automatically generates implementation templates for the modelled multiagent system. This way, the need for extensive manual coding may be somewhat reduced, ensuring that conceptual integrity is maintained throughout development. A case study showcases how the proposed framework may speed up the design cycle, reduce coding errors, and enhance system extensibility. Using ontology-driven generation ensures consistency and interoperability, as each agent artefact follows the established domain semantics. This approach may be especially beneficial in complex, knowledge-intensive environments that require collaborative and distributed solutions. Ultimately, it may lead to a flexible and scalable process from domain modelling to multiagent implementation. Our framework provides a way that might help bridge the gap between conceptual design and agent-based execution, streamlining multiagent system development and ensuring robust alignment with domainspecific ontologies.