Andrea Omicini

Task-oriented engineering of coordinated software systems

Enrico Denti, Andrea Omicini, Alessandro Ricci

In the context of Internet-based applications where heterogeneous, legacy entities should integrate and cooperate, the efficiency of the software production process is a key problem: yet, the classical development cycle and methodologies fall short, calling for ad hoc abstractions, methodologies and tools. …

Intelligent Agents from Symbolic to Neurosymbolic Systems: The Quest for Integration

Andrea Agiollo, Roberta Calegari, Giovanni Ciatto, Matteo Magnini et autres

In this chapter we take as our reference twenty-five years of scientific and technical results presented at the Workshop on Objects, and explore the development of rational agents and integration with machine learning (ML) techniques, discussing their transition from pure symbolic to …

nl, it (code pays fourni par la source)

AI Infrastructure: From Gigastructure to Edge Intelligence with Multi-Agent Systems

Andrea Omicini, Alessandro Ricci, Viviana Mascardi

The rise of generative AI and LLMs is reshaping the global landscape of computational infrastructures. Massive investments in hardware and software are required, raising pressing questions about technological monopolies, digital divides, and the role of public institutions. Recalling the historical evolution of …

it (code pays fourni par la source)

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

Andrea Agiollo, Andrea Omicini

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 …

ECAI 2025

Inês Lynce, Nello Murano, Mauro Vallati, Serena Villata et autres

Attribution is crucial in question answering (QA) with Large Language Models (LLMs).SOTA question decomposition-based approaches use long form answers to generate questions for retrieving related documents. However, the generated questions are often irrelevant and incomplete, resulting in a loss of facts in …

Large language models as oracles for instantiating ontologies with domain-specific knowledge

Giovanni Ciatto, Andrea Agiollo, Matteo Magnini, Andrea Omicini

Background. Endowing intelligent systems with semantic data commonly requires designing and instantiating ontologies with domain-specific knowledge. Especially in the early phases, those activities are typically performed manually by human experts possibly leveraging on their own experience. The resulting process is therefore time-consuming, …

A Domain-Specific Language for NeSy Focussing on Symbolic Knowledge Injection

Mattia Matteini, Giovanni Ciatto, Matteo Magnini, Emre Kuru et autres

In neuro-symbolic AI (NeSy), integrating symbolic languages – typically subsets of first-order logic (FOL) –, with neural networks (NNs) serves goals like enhancing symbolic processing, extending reasoning with pattern recognition, and guiding neural learning with symbolic knowledge—a.k.a. symbolic knowledge injection (SKI). Despite …

it, tr (code pays fourni par la source)

From large language models to small logic programs: building global explanations from disagreeing local post-hoc explainers

Andrea Agiollo, Luciano Cavalcante Siebert, Pradeep Kumar Murukannaiah, Andrea Omicini

Abstract The expressive power and effectiveness of large language models (LLMs) is going to increasingly push intelligent agents towards sub-symbolic models for natural language processing (NLP) tasks in human–agent interaction. However, LLMs are characterised by a performance vs. transparency trade-off that hinders …

it, nl (code pays fourni par la source)

Intelligent Agents and Environment

Alfredo Garro, Alberto Falcone, Matteo Baldoni, Cristina Baroglio et autres

it (code pays fourni par la source)

Intelligent Agents: Multi-Agent Systems

Alfredo Garro, Alberto Falcone, Matteo Baldoni, Cristina Baroglio et autres

it (code pays fourni par la source)

Concurrency Model of BDI Programming Frameworks: Why Should We Control It?

Martina Baiardi, Samuele Burattini, Giovanni Ciatto, Danilo Pianini et autres

We provide a taxonomy of concurrency models for BDI frameworks, elicited by analysing state-of-the-art technologies, and aimed at helping both BDI designers and developers in making informed decisions. Comparison among BDI technologies w.r.t. concurrency models reveals heterogeneous support, and low customisability.

it (code pays fourni par la source)

Concurrency Model of BDI Programming Frameworks: Why Should We Control It?

Martina Baiardi, Samuele Burattini, Giovanni Ciatto, Danilo Pianini et autres

We provide a taxonomy of concurrency models for BDI frameworks, elicited by analysing state-of-the-art technologies, and aimed at helping both BDI designers and developers in making informed decisions. Comparison among BDI technologies w.r.t. concurrency models reveals heterogeneous support, and low customisability.