Integrating Machine Learning into Belief-Desire-Intention Agents: Current Advances and Open Challenges

TL;DR

This paper reviews how machine learning is integrated into Belief-Desire-Intention (BDI) rational agents, highlighting current approaches, challenges, and future research directions in this evolving field.

Contribution

It provides a detailed systematisation of existing methods of embedding ML into BDI agents, emphasizing the expressive power and design challenges of rational architectures.

Findings

The literature on ML-enhanced rational agents is rapidly evolving.

Current approaches often lack coherence and focus on generic agent frameworks.

Open challenges include designing effective, expressive rational ML agents.

Abstract

Thanks to the remarkable human-like capabilities of machine learning (ML) models in perceptual and cognitive tasks, frameworks integrating ML within rational agent architectures are gaining traction. Yet, the landscape remains fragmented and incoherent, often focusing on embedding ML into generic agent containers while overlooking the expressive power of rational architectures--such as Belief-Desire-Intention (BDI) agents. This paper presents a fine-grained systematisation of existing approaches, using the BDI paradigm as a reference. Our analysis illustrates the fast-evolving literature on rational agents enhanced by ML, and identifies key research opportunities and open challenges for designing effective rational ML agents.