The Belief-Desire-Intention Ontology for modelling mental reality and agency

TL;DR

This paper introduces a formal BDI Ontology designed to model cognitive agent architectures with semantic precision, enabling integration with LLMs and reasoning platforms for more explainable and interoperable AI systems.

Contribution

It presents a modular, formally aligned BDI Ontology that enhances semantic interoperability and demonstrates its practical application with LLMs and reasoning systems.

Findings

Ontology improves inferential coherence with LLMs

Enables bidirectional reasoning between RDF and mental states

Facilitates explainable, interoperable multi-agent systems

Abstract

The Belief-Desire-Intention (BDI) model is a cornerstone for representing rational agency in artificial intelligence and cognitive sciences. Yet, its integration into structured, semantically interoperable knowledge representations remains limited. This paper presents a formal BDI Ontology, conceived as a modular Ontology Design Pattern (ODP) that captures the cognitive architecture of agents through beliefs, desires, intentions, and their dynamic interrelations. The ontology ensures semantic precision and reusability by aligning with foundational ontologies and best practices in modular design. Two complementary lines of experimentation demonstrate its applicability: (i) coupling the ontology with Large Language Models (LLMs) via Logic Augmented Generation (LAG) to assess the contribution of ontological grounding to inferential coherence and consistency; and (ii) integrating the ontology within the Semas reasoning platform, which implements the Triples-to-Beliefs-to-Triples (T2B2T) paradigm, enabling a bidirectional flow between RDF triples and agent mental states. Together, these experiments illustrate how the BDI Ontology acts as both a conceptual and operational bridge between declarative and procedural intelligence, paving the way for cognitively grounded, explainable, and semantically interoperable multi-agent and neuro-symbolic systems operating within the Web of Data.