The Belief-Desire-Intention Ontology for modelling mental reality and agency
🤖 AI Summary
The Belief-Desire-Intention (BDI) model lacks seamless integration into semantic interoperability frameworks due to its informal, procedural nature and absence of standardized ontological grounding.
Method: We propose a formal, modular BDI ontology design pattern that explicitly axiomatizes the cognitive structures of beliefs, desires, and intentions—and their dynamic evolution—by innovatively integrating Logic-Augmented Generation (LAG), large language models, and RDF triples to establish a bidirectional Translation-to-Belief-to-Translation (T2B2T) mechanism linking symbolic knowledge and agent belief states. This is implemented atop the Semas neurosymbolic reasoning platform.
Contribution/Results: We present the first reusable, ontology-based BDI formalization, bridging the gap between declarative knowledge representation and procedural reasoning. Empirical evaluation demonstrates improved multi-agent reasoning consistency and enables semantically aligned, bidirectional mapping between data-layer facts and mental-state representations—establishing an interpretable, interoperable infrastructure for Web-scale cognitive intelligent systems.
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
Limited integration of BDI model into structured knowledge representations
Need for semantic precision in representing agent cognitive architecture
Bridging declarative and procedural intelligence for explainable AI systems
Innovation
Methods, ideas, or system contributions that make the work stand out.
Formal BDI Ontology as modular design pattern
Coupling ontology with LLMs via Logic Augmented Generation
Integrating ontology with Semas T2B2T reasoning platform
🔎 Similar Papers
No similar papers found.
