Samuele Burattini

AAMAS Conference 2026 Conference Paper

A Multi-level Explainability Framework for Engineering and Understanding BDI Agents

• Elena Yan
• Samuele Burattini
• Jomi F. Hübner
• Alessandro Ricci

As the complexity of software systems rises, the ability to provide explanations of system behavior has become a desirable property for any Artificial Intelligence based system, including autonomous multi-agent systems. While explainability is mainly explored to increase trust and understanding for end-users, it is also an interesting property from a software engineering perspective, supporting developers and designers in the debugging and validation phases. To address the different needs and expertise of these roles, we propose a framework that generates explanations at multiple levels of abstraction, enabling both the engineering and the understanding of BDI agents.

JAAMAS Journal 2026 Journal Article

Testing BDI-based multi-agent systems using discrete event simulation

• Martina Baiardi
• Samuele Burattini
• Danilo Pianini

Abstract Multi-agent systems are designed to deal with open, distributed systems with unpredictable dynamics, which makes them inherently hard to test. The value of using simulation for this purpose is recognized in the literature, although achieving sufficient fidelity (i. e. , the degree of similarity between the simulation and the real-world system) remains a challenging task. This is exacerbated when dealing with cognitive agent models, such as the Belief Desire Intention (BDI) model, where the agent codebase is not suitable to run unchanged in simulation environments, thus increasing the reality gap between the deployed and simulated systems. We argue that BDI developers should be able to test in simulation the same specification that will be later deployed, with no surrogate representations. Thus, in this paper, we discuss how the control flow of BDI agents can be mapped onto a Discrete Event Simulation (DES), showing that such integration is possible at different degrees of granularity. We substantiate our claims by producing an open-source prototype integration between two pre-existing tools (JaKtA and Alchemist), showing that it is possible to produce a simulation-based testing environment for distributed BDI agents, and that different granularities in mapping BDI agents over DESs may lead to different degrees of fidelity.

JAAMAS Journal 2025 Journal Article

A multi-level explainability framework for engineering and understanding BDI agents

• Elena Yan
• Samuele Burattini
• Alessandro Ricci

Abstract As the complexity of software systems rises, explainability - i. e. the ability of systems to provide explanations of their behaviour - becomes a crucial property. This is true for any AI-based systems, including autonomous systems that exhibit decisionmaking capabilities such as multi-agent systems. Although explainabil- ity is generally considered useful to increase the level of trust for end-users, we argue it is also an interesting property for software engineers, developers, and designers to debug and validate the system’s behaviour. In this paper, we propose a multi-level explainability framework for BDI agents to generate explanations of a running system from logs at different levels of abstraction, tailored to different users and their needs. We describe the mapping from logs to explanations, and present a prototype tool based on the JaCaMo platform which implements the framework.

EUMAS Conference 2025 Conference Paper

Agent Toolkits: Towards Explainable Agency in ASTRA

• Katharine Beaumont
• Elena Yan
• Samuele Burattini
• Rem W. Collier

ECAI Conference 2025 Conference Paper

Exploiting GenAI for Plan Generation in BDI Agents

• Giovanni Ciatto
• Gianluca Aguzzi
• Riccardo Battistini
• Martina Baiardi
• Samuele Burattini
• Alessandro Ricci

Extending BDI agents with the ability to autonomously generate plans has long been a goal in the field of cognitive agent engineering to enhance their adaptability. Recent advances in GenAI are now opening new possibilities for plan generation, by leveraging the natural-language understanding, mean-end reasoning, and abstraction capabilities of LLMs. In this paper, we investigate the integration of GenAI-based plan generation into AgentSpeak(L) agents, and we analyse the implications of transferring knowledge between the LLM and the BDI agent, for the sake of dynamic plan generation. We propose a coherent framework where AgentSpeak(L) is extended with plan generation, and we model the boundaries of the generative process. We prototype our framework via the JaKtA BDI agent technology, and we methodologically assess the quality of the plans generated by LLMs of different sorts.

EUMAS Conference 2025 Conference Paper

Extending CArtAgO to support the engineering of complex distributed environments at the Knowledge Level

• Alessandro Ricci
• Andrei Ciortea
• Samuele Burattini

JAAMAS Journal 2025 Journal Article

Reflexive anticipatory reasoning by BDI agents

• Jomi Fred Hübner
• Samuele Burattini
• Simon Mayer

Abstract This paper investigates how predictions about the future behaviour of an agent can be exploited to improve its decision-making in the present. Future states are foreseen by a simulation technique, which is based on models of both the environment and the agent. Although the environment model is usually taken into account for prediction in artificial intelligence (e. g. , in automated planning), the agent model receives less attention. We leverage the agent model to speed up the simulation and as a source of alternative decisions. Our proposal bases the agent model on the practical knowledge the developer has given to the agent, especially in the case of BDI agents. This knowledge is thus exploited in the proposed future-concerned reasoning mechanisms. We present a prototype implementation of our approach as well as the results from its evaluation on static and dynamic environments. This allows us to better understand the relation between the improvement in agent decisions and the quality of the knowledge provided by the developer.

AAMAS Conference 2024 Conference Paper

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

• Martina Baiardi
• Samuele Burattini
• Giovanni Ciatto
• Danilo Pianini
• Andrea Omicini
• Alessandro Ricci

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.

AAMAS Conference 2024 Conference Paper

The Cognitive Hourglass: Agent Abstractions in the Large Models Era

• Alessandro Ricci
• Stefano Mariani
• Franco Zambonelli
• Samuele Burattini
• Cristiano Castelfranchi

Recent advances in AI are driving an unprecedented and fastpaced development of myriads of powerful agent tools and applications, mostly based on generative AI technologies such as Large Language/Multi-modal/Agent Models. However, despite many proposals in that direction, the lack of a sound set of usable engineering abstractions hinders the possibility of methodically engineering complex agent-based applications, also due to the gap between cognitive agent-based concepts and LLMs’ behavioural patterns. We argue that such a set of abstractions should constitute the narrow neck of an indispensable “cognitive hourglass”: a level of abstraction that is meant to be useful for humans to understand/design/control agents and MAS, regardless of the specific AI technologies adopted at the implementation level and of the specific application context. Here, we elaborate on the idea of the cognitive hourglass, motivate its need, sketch its envisioned architecture, and identify the research challenges for its realisation.

EUMAS Conference 2024 Conference Paper

Towards Agents' Embodiment in Hypermedia Multi-agent Systems

• Matteo Castellucci
• Samuele Burattini
• Andrei Ciortea
• Jérémy Lemée
• Danai Vachtsevanou
• Alessandro Ricci
• Simon Mayer

Abstract Situatedness and embodiment are central features of autonomous agents, initially inspired by agents operating in physical environments. In this paper, we discuss the benefits of situated and embodied agents in digital environments. More specifically, we study the embodiment of agents in Web-based Multi-Agent Systems (MAS). Such MAS are inherently open and distributed, as they inherit these properties from the Web, and increasingly dynamic, as they can easily extend to physical environments through the Web of Things. We propose a conceptualization of agent bodies in such Web environments and discuss their properties. We illustrate our approach through a demonstration scenario implemented using the Yggdrasil framework for Hypermedia MAS, a subset of Web-based MAS that follows a hypermedia-based design rationale.

AAMAS Conference 2023 Conference Paper

Domain-Expert Configuration of Hypermedia Multi-Agent Systems in Industrial Use Cases

• Jérémy Lemée
• Samuele Burattini
• Simon Mayer
• Andrei Ciortea

Based on the analysis of two real-world use cases for agriculture and manufacturing, we suggest that Hypermedia Multi-Agent Systems (MAS) are a viable option to interconnect and coordinate devices, services, machine-learning systems, and people in industrial scenarios. We propose and implement an architecture based on three components: an infrastructure that manages Web of Things environments and executes Hypermedia MAS, a visual development environment for programming agents, and a goal specification interface for end-users. While the infrastructure manages information flows between the system components and provides an environment for agents, the visual language enables domain experts to configure the behaviour of the system leveraging agent-oriented programming abstractions both at design time and run time, and the goal specification interface permits users to delegate goals to the running Hypermedia MAS while re-using domain vocabulary.

EUMAS Conference 2023 Conference Paper

JaKtA: BDI Agent-Oriented Programming in Pure Kotlin

• Martina Baiardi
• Samuele Burattini
• Giovanni Ciatto
• Danilo Pianini

Abstract Multi-paradigm languages are becoming more and more popular, as they allow developers to choose the most suitable paradigm for each task. Most commonly, we observe the combination of object-oriented (OOP) and functional programming (FP), however, in principle, other paradigms could be hybridised. In this paper, we present JaKtA, an internal DSL adding support for the definition of belief-desire-intention (BDI) agents in Kotlin. We believe is a first step to investigate the blending of Agent-Oriented Programming (AOP) with other popular paradigms and we discuss the opportunity and value of doing so with an internal DSLs. Finally, through JaKtA, we show how this can already lead to compactly and expressively create BDI agents that smoothly interoperate with the host language, its libraries and tooling.

EUMAS Conference 2023 Conference Paper

Supporting Adaptive Multi-Agent Systems with Digital Twins Environments

• Samuele Burattini

Abstract Adaptability is an essential feature of autonomous agents, especially when considering the interaction with the real world which is, by definition, dynamic and unpredictable. To support adaptation in real-world scenarios self-describing Digital Twins with simulation and prediction abilities could be exploited to build the environment of a multi-agent system. A roadmap is presented, reflecting on the role of the environment in the development of multi-agent systems, its potential integration with Digital Twins and suggesting the need for a generalised model for adaptive agents that could leverage the features offered by such Digital Twins environment.