In this paper we describe ChatBDI, a framework for extending Belief-Desire-Intention (BDI) agents implemented in Jason with the ability to understand and generate messages in natural language by exploiting embeddings and Large Language Models (LLMs). Thanks to the generative power of LLMs, the ‘chattification’ of new or legacy multiagent systems (MAS) adds a creative and fluent ‘language actuator’ to BDI agents and serves two main purposes. First, it allows users to enter the MAS and conversate with any other software agent in natural language, as if humans were agents themselves. Second, it allows both the MAS developers and the users to follow the conversation among software agents and to ask them information on their behavior and decisions, acting as a lightweight co-pilot and improving transparency and explainability. The major strength of ChatBDI, and its distinguishing feature w.r.t. related works, is its general purpose nature: by exploiting plan injection and sophisticated meta-programming facilities, ChatBDI can be used to chattify any MAS implemented in Jason or JaCaMo with neither adaptations of the ChatBDI code itself, nor changes to the existing AgentSpeak(L) agents’ source code.

Most mainstream object-oriented languages provide a notion of equality between objects which can be customized to be weaker than reference equality, and which is coupled with the customizable notion of object hash code. This feature is so pervasive in object-oriented code that incorrect redefinition or use of equality and hash code may have a serious impact on software reliability and safety.

Abstract Precisely when the success of artificial intelligence (AI) sub-symbolic techniques makes them be identified with the whole AI by many non-computer-scientists and non-technical media, symbolic approaches are getting more and more attention as those that could make AI amenable to human understanding. Given the recurring cycles in the AI history, we expect that a revamp of technologies often tagged as “classical AI”—in particular, logic-based ones—will take place in the next few years. On the other hand, agents and multi-agent systems (MAS) have been at the core of the design of intelligent systems since their very beginning, and their long-term connection with logic-based technologies , which characterised their early days, might open new ways to engineer explainable intelligent systems . This is why understanding the current status of logic-based technologies for MAS is nowadays of paramount importance. Accordingly, this paper aims at providing a comprehensive view of those technologies by making them the subject of a systematic literature review (SLR). The resulting technologies are discussed and evaluated from two different perspectives: the MAS and the logic-based ones.

Abstract A computational system is called autonomous if it is able to make its own decisions, or take its own actions, without human supervision or control. The capability and spread of such systems have reached the point where they are beginning to touch much of everyday life. However, regulators grapple with how to deal with autonomous systems, for example how could we certify an Unmanned Aerial System for autonomous use in civilian airspace? We here analyse what is needed in order to provide verified reliable behaviour of an autonomous system, analyse what can be done as the state-of-the-art in automated verification, and propose a roadmap towards developing regulatory guidelines, including articulating challenges to researchers, to engineers, and to regulators. Case studies in seven distinct domains illustrate the article.

Abstract This paper presents an extension of the Predictive Runtime Verification (PRV) paradigm to consider multiple models of the System Under Analysis (SUA). We call this extension Multi-Model PRV. Typically, PRV attempts to predict the satisfaction or violation of a property based on a trace and a (single) formal model of the SUA. However, contemporary node- or component-based systems (e.g. robotic systems) may benefit from monitoring based on a model of each component. We show how a Multi-Model PRV approach can be applied in either a centralised or a compositional way (where the property is compositional), as best suits the SUA. Crucially, our approach is formalism-agnostic. We demonstrate our approach using an illustrative example of a Mars Curiosity rover simulation and evaluate our contribution via a prototype implementation.

When applying formal verification to a system that interacts with the real world, we must use a model of the environment. This model represents an abstraction of the actual environment, so it is necessarily incomplete and hence presents an issue for system verification. If the actual environment matches the model, then the verification is correct; however, if the environment falls outside the abstraction captured by the model, then we cannot guarantee that the system is well behaved. A solution to this problem consists in exploiting the model of the environment used for statically verifying the system’s behaviour and, if the verification succeeds, using it also for validating the model against the real environment via runtime verification. The article discusses this approach and demonstrates its feasibility by presenting its implementation on top of a framework integrating the Agent Java PathFinder model checker. A high-level Domain Specific Language is used to model the environment in a user-friendly way; the latter is then compiled to trace expressions for both static formal verification and runtime verification. To evaluate our approach, we apply it to two different case studies: an autonomous cruise control system and a simulation of the Mars Curiosity rover.

We present OntoScene, a framework aimed at understanding the semantics of visual scenes starting from the semantics of their elements and the spatial relations holding between them. OntoScene exploits ontologies for representing knowledge and Prolog for specifying the interpretation rules that domain experts may adopt, and for implementing the SceneInterpreter engine. Ontologies allow the designer to formalize the domain in a reusable way and make the system modular and interoperable with existing multiagent systems, while Prolog provides a solid basis to define complex rules of interpretation in a way that can be affordable even for people with no background in Computational Logics. The domain selected for experimenting OntoScene is that of prehistoric rock art, which provides us with a fascinating and challenging testbed.

Parametric trace expressions are a formalism expressly designed for parametric runtime verification (RV) which has been introduced and successfully employed in the context of runtime monitoring of multiagent systems.

Summary This paper describes IndianaMAS, a multiagent system able to automatically classify and manage images, sketches, and multilingual documents in a cultural heritage domain. The latter has been formalized by means of an ontology, which enables the semantic integration of heterogeneous data from different sources, drives the agent communication with the internal and external environment, and provides an abstract and human‐readable interface between the system and the user. IndianaMAS is able to expose to the world the classified data via a digital library. Modularity and reusability are the key engineering principles followed in the system design and implementation. We present the details of the IndianaMAS system and discuss how its architecture can be generalized to create – with the minimal effort – systems addressing similar classification, storage, and management problems, but operating in different domains and driven by different ontologies. The concrete problems we faced and their solutions are described to share our lesson learned and, at the same time, to show the applicability and reusability of our modular approach based on ontologies, agents, and digital libraries. Copyright © 2017 John Wiley & Sons, Ltd.

In this paper we present CooL-AgentSpeak, an extension of AgentSpeak-DL with plan exchange and ontology services. In CooL-AgentSpeak, the search for an ontologically relevant plan is no longer limited to the agent's local plan library but is carried

With the invention and rapid improvement of data-capturing devices, such as satellite imagery and digital cameras, the information that archaeologists must manage in their everyday's activities has rapidly grown in complexity and amount. In this work we present Indiana Finder, an interactive visualization system that supports archaeologists in the examination of large repositories of documents and drawings. In particular, the system provides visual analytic support for investigative analysis such as the interpretation of new archaeological findings, the detection of interpretation anomalies, and the discovery of new insights. We illustrate the potential of Indiana Finder in the context of the digital protection and conservation of rock art natural and cultural heritage sites. In this domain, Indiana Finder provides an integrated environment that archaeologists can exploit to investigate, discover, and learn from textual documents, pictures, and drawings related to rock carvings. This goal is accomplished through novel visualization methods including visual similarity ring charts that may help archaeologists in the hard task of dating a symbol in a rock engraving based on its shape and on the surrounding symbols.

“Ontology matching” is the process of finding correspondences between entities belonging to different ontologies. This paper describes a set of algorithms that exploit upper ontologies as semantic bridges in the ontology matching process and presents a systematic analysis of the relationships among features of matched ontologies (number of simple and composite concepts, stems, concepts at the top level, common English suffixes and prefixes, and ontology depth), matching algorithms, used upper ontologies, and experiment results. This analysis allowed us to state under which circumstances the exploitation of upper ontologies gives significant advantages with respect to traditional approaches that do no use them. We run experiments with SUMO-OWL (a restricted version of SUMO), OpenCyc, and DOLCE. The experiments demonstrate that when our “structural matching method via upper ontology” uses an upper ontology large enough (OpenCyc, SUMO-OWL), the recall is significantly improved while preserving the precision obtained without upper ontologies. Instead, our “nonstructural matching method” via OpenCyc and SUMO-OWL improves the precision and maintains the recall. The “mixed method” that combines the results of structural alignment without using upper ontologies and structural alignment via upper ontologies improves the recall and maintains the F-measure independently of the used upper ontology.

In this paper we present AgentSketch, an agent- based system for on-line recognition of hand-drawn diagrams. Agents are used for managing the activity of symbol recognizers and for providing efficient interpretations of the sketch to the user thanks to the use of contextual information for ambiguity resolution. The system can be applied to a variety of domains by providing recognizers of the symbols in that domain. A first experimental evaluation has been performed on the domain of UML use case diagrams to verify the effectiveness of the proposed approach.

Parsing hand-drawn diagrams is a definitely complex recognition problem. The input drawings are often intrinsically ambiguous, and require context to be interpreted in a correct way. Many existing sketch recognition systems avoid this problem by recognizing single segments or simple geometric shapes in a stroke. However, for a recognition system to be effective and precise, context must be exploited, and both the simplifications on the sketch features, and the constraints under which recognition may take place, must be reduced to the minimum. In this paper we present an agent-based framework for context-driven interpretation of symbols in diagrammatic sketches that heavily exploits contextual information for ambiguity resolution. Agents manage the activity of low-level hand-drawn symbol recognizers, that may be heterogeneous for better adapting to the characteristics of each symbol to be recognized, and coordinate themselves in order to exchange contextual information, thus leading to an efficient and precise interpretation of sketches

The research field of Agent-Oriented Software Engineering (AOSE) aims to find abstractions, languages, methodologies and toolkits for modeling, verifying, validating and prototyping complex applications conceptualized as Multiagent Systems (MASs). A very lively research sub-field studies how formal methods can be used for AOSE. This paper presents a detailed survey of six logic-based executable agent specification languages that have been chosen for their potential to be integrated in our ARPEGGIO project, an open framework for specifying and prototyping a MAS. The six languages are $\textsf{ConGolog}$ , $\textsf{AGENT-0}$ , the $\textsf{IMPACT}$ agent programming language, $\textsf{DyLOG}$ , Concurrent $\textsf{METATEM}$ and ${\cal E}_{hhf}$ . For each executable language, the logic foundations are described and an example of use is shown. A comparison of the six languages and a survey of similar approaches complete the paper, together with considerations of the advantages of using logic-based languages in MAS modeling and prototyping.