The Belief-Desire-Intention Ontology for modelling mental reality and agency
Sara Zuppiroli, Carmelo Fabio Longo, Anna Sofia Lippolis, Rocco Paolillo, Lorenzo Giammei, Miguel Ceriani, Francesco Poggi, Antonio Zinilli, Andrea Giovanni Nuzzolese
TL;DR
The paper addresses the challenge of semantically interoperable representations of agent rationality by introducing the BDI Ontology as a modular Ontology Design Pattern that encodes beliefs, desires, intentions, goals, and their dynamics. It combines rigorous formalisation with alignment to DOLCE UltraLite and demonstrates practical utility through two lines of experimentation: LAG aided reasoning with LLMs and executable reasoning within the Semas BDI framework via the T2B2T paradigm. The results show enhanced inferential coherence, explainability, and seamless integration between declarative knowledge graphs and procedural reasoning, supporting cognitively grounded, semantically interoperable AI in multi-agent and neuro-symbolic contexts. These contributions lay groundwork for explainable, interoperable agency on the Web of Data and point to future work on conflicts, broader domain applications, and scalable tooling.
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.