Modern Trends in Multi-Agent Systems


The issue "Modern Trends in Multi-Agent Systems" is a special issue of Future Internet MDPI. Manuscripts should be submitted online at by registering and logging in to this website. Once you are registered, click here to go to the submission form. The deadline for submission is 31st December 2022 (EXTENDED !!!)



Dear Colleagues,

In general, the term "multi-agent system" (referred to as MAS) is understood as an interconnected set of independent entities that are able to effectively solve complex and time-consuming problems exceeding the individual abilities of common problem solvers. The coordinated entities forming MAS regularly interact with each other in order to solve various problems in numerous technical/non-technical applications. In many modern MASs, the entities are required to be fully autonomous, to provide global decisions based on local knowledge, and to be able to work effectively in a decentralized way. The design of robust, energy-efficient, and high-performance algorithms for MASs, therefore, poses a demanding challenge for the wider scientific community. Thus, significant attention has been paid by many scientists to optimizing the operation of MASs in many respects (e.g., routing, data aggregation, communication, coordination, consensus achievement, synchronization, etc.) over recent decades.

This special issue is dedicated to the analysis and the optimization of multi-agent systems from a wide point of view (including also branches potentially applicable in multi-agent systems); therefore, potential topics include but are not limited to the following:

  • wireless networks
  • Internet of Things
  • distributed and parallel computing
  • cloud computing
  • data aggregation, sensor fusion
  • signal processing
  • modeling by the big data from the multi-sensor systems
  • possibility theory
  • remote sensing data processing
  • artificial intelligence for the multi-sensor fusion systems
  • routing protocols
  • communication protocols
  • optical systems
  • etc.

Guest Editors: Prof. Dr. Agostino Poggi, Dr. Martin Kenyeres, Dr. Ivana Budinská, and
Dr. Ladislav Hluchý

Click here to find out more details about our special issue

Click here to download the official flyer

See social media:

For further information, feel free to contact us:



A Multi-Agent Approach to Binary Classification Using Swarm Intelligence

by Sean Grimes and David E. Breen

Abstract: Wisdom-of-Crowds-Bots (WoC-Bots) are simple, modular agents working together in a multi-agent environment to collectively make binary predictions. The agents represent a knowledge-diverse crowd, with each agent trained on a subset of available information. A honey-bee-derived swarm aggregation mechanism is used to elicit a collective prediction with an associated confidence value from the agents. Due to their multi-agent design, WoC-Bots can be distributed across multiple hardware nodes, include new features without re-training existing agents, and the aggregation mechanism can be used to incorporate predictions from other sources, thus improving overall predictive accuracy of the system. In addition to these advantages, we demonstrate that WoC-Bots are competitive with other top classification methods on three datasets and apply our system to a real-world sports betting problem, producing a consistent return on investment from 1 January 2021 through 15 November 2022 on most major sports.

see the paper >>>

Pedestrian Simulation with Reinforcement Learning: A Curriculum-Based Approach
by Giuseppe Vizzari and Thomas Cecconello

Abstract: Pedestrian simulation is a consolidated but still lively area of research. State of the art models mostly take an agent-based perspective, in which pedestrian decisions are made according to a manually defined model. Reinforcement learning (RL), on the other hand, is used to train an agent situated in an environment how to act so as to maximize an accumulated numerical reward signal (a feedback provided by the environment to every chosen action). We explored the possibility of applying RL to pedestrian simulation. We carefully defined a reward function combining elements related to goal orientation, basic proxemics, and basic way-finding considerations. The proposed approach employs a particular training curriculum, a set of scenarios growing in difficulty supporting an incremental acquisition of general movement competences such as orientation, walking, and pedestrian interaction. The learned pedestrian behavioral model is applicable to situations not presented to the agents in the training phase, and seems therefore reasonably general. This paper describes the basic elements of the approach, the training procedure, and an experimentation within a software framework employing Unity and ML-Agents.

see the paper >>>

Co-Simulation of Multiple Vehicle Routing Problem Models
by Sana Sahar Guia, Abdelkader Laouid, Mohammad Hammoudeh, Ahcène Bounceur, Mai Alfawair, and Amna Eleyan 

Abstract: Complex systems are often designed in a decentralized and open way so that they can operate on heterogeneous entities that communicate with each other. Numerous studies consider the process of components simulation in a complex system as a proven approach to realistically predict the behavior of a complex system or to effectively manage its complexity. The simulation of different complex system components can be coupled via co-simulation to reproduce the behavior emerging from their interaction. On the other hand, multi-agent simulations have been largely implemented in complex system modeling and simulation. Each multi-agent simulator’s role is to solve one of the VRP objectives. These simulators interact within a co-simulation platform called MECSYCO, to ensure the integration of the various proposed VRP models. This paper presents the Vehicle Routing Problem (VRP) simulation results in several aspects, where the main goal is to satisfy several client demands. The experiments show the performance of the proposed VRP multi-model and carry out its improvement in terms of computational complexity.

see the paper >>>

On the Use of the Multi-Agent Environment for Mobility Applications
by Mahdi Zargayouna
Abstract: The multi-agent environment is now widely recognised as a key design abstraction for constructing multi-agent systems, equally important as the agents. An explicitly designed environment may have several roles, such as the inter-mediation between agents, the support for interaction, the embodiment of rules and constraints, etc. Mobility applications fit perfectly with a design in the form of a multi-agent system with an explicit environment model. Indeed, in these applications, the components of the system are autonomous and intelligent (drivers, travellers, vehicles, etc.), and the transportation network is a natural environment that they perceive and on which they act. However, the concept of the multi-agent environment may be profitably used beyond this specific geographical context. This paper discusses the relevance of the multi-agent environment in mobility applications and describes different use cases in simulation and optimisation.

see the paper >>>

High-Performance Computing and ABMS for High-Resolution COVID-19 Spreading Simulation
by Mattia Pellegrino, Gianfranco Lombardo, Stefano Cagnoni and Agostino Poggi
Abstract: This paper presents an approach for the modeling and the simulation of the spreading of COVID-19 based on agent-based modeling and simulation (ABMS). Our goal is not only to support large-scale simulations but also to increase the simulation resolution. Moreover, we do not assume an underlying network of contacts, and the person-to-person contacts responsible for the spreading are modeled as a function of the geographical distance among the individuals. In particular, we defined a commuting mechanism combining radiation-based and gravity-based models and we exploited the commuting properties at different resolution levels (municipalities and provinces). Finally, we exploited the high-performance computing (HPC) facilities to simulate millions of concurrent agents, each mapping the individual’s behavior. To do such simulations, we developed a spreading simulator and validated it through the simulation of the spreading in two of the most populated Italian regions: Lombardy and Emilia-Romagna. Our main achievement consists of the effective modeling of 10 million of concurrent agents, each one mapping an individual behavior with a high-resolution in terms of social contacts, mobility and contribution to the virus spreading. Moreover, we analyzed the forecasting ability of our framework to predict the number of infections being initialized with only a few days of real data. We validated our model with the statistical data coming from the serological analysis conducted in Lombardy, and our model makes a smaller error than other state of the art models with a final root mean squared error equal to 56,009 simulating the entire first pandemic wave in spring 2020. On the other hand, for the Emilia-Romagna region, we simulated the second pandemic wave during autumn 2020, and we reached a final RMSE equal to 10,730.11.

see the paper >>>

Graphol: A Graphical Language for Ontology Modeling Equivalent to OWL 2
by Domenico Lembo, Valerio Santarelli, Domenico Fabio Savo and Giuseppe De Giacomo
Abstract: In this paper we study Graphol, a fully graphical language inspired by standard formalisms for conceptual modeling, similar to the UML class diagram and the ER model, but equipped with formal semantics. We formally prove that Graphol is equivalent to OWL 2, i.e., it can capture every OWL 2 ontology and vice versa. We also present some usability studies indicating that Graphol is suitable for quick adoption by conceptual modelers that are familiar with UML and ER. This is further testified by the adoption of Graphol for ontology representation in several industrial projects.

see the paper >>>

Topology Inference and Link Parameter Estimation Based on End-to-End Measurements
by Grigorios Kakkavas, Vasileios Karyotis and Symeon Papavassiliou
Abstract: This paper focuses on the design, implementation, experimental validation, and evaluation of a network tomography approach for performing inferential monitoring based on indirect measurements. In particular, we address the problems of inferring the routing tree topology (both logical and physical) and estimating the links’ loss rate and jitter based on multicast end-to-end measurements from a source node to a set of destination nodes using an agglomerative clustering algorithm. The experimentally-driven evaluation of the proposed algorithm, particularly the impact of the employed reduction update scheme, takes place in real topologies constructed in an open large-scale testbed. Finally, we implement and present a motivating practical application of the proposed algorithm that combines monitoring with change point analysis to realize performance anomaly detection. 

see the paper >>>

Architecting an Agent-Based Fault Diagnosis Engine for IEC 61499 Industrial Cyber-Physical Systems
by Barry Dowdeswell, Roopak Sinha and Stephen G. MacDonell
Abstract: IEC 61499 is a reference architecture for constructing Industrial Cyber-Physical Systems (ICPS). However, current function block development environments only provide limited fault-finding capabilities. There is a need for comprehensive diagnostic tools that help engineers identify faults, both during development and after deployment. This article presents the software architecture for an agent-based fault diagnostic engine that equips agents with domain-knowledge of IEC 61499. The engine encourages a Model-Driven Development with Diagnostics methodology where agents work alongside engineers during iterative cycles of design, development, diagnosis and refinement. Attribute-Driven Design (ADD) was used to propose the architecture to capture fault telemetry directly from the ICPS. A Views and Beyond Software Architecture Document presents the architecture. The Architecturally-Significant Requirement (ASRs) were used to design the views while an Architectural Trade-off Analysis Method (ATAM) evaluated critical parts of the architecture. The agents locate faults during both early-stage development and later provide long-term fault management. The architecture introduces dynamic, low-latency software-in-loop Diagnostic Points (DPs) that operate under the control of an agent to capture fault telemetry. Using sound architectural design approaches and documentation methods, coupled with rigorous evaluation and prototyping, the article demonstrates how quality attributes, risks and architectural trade-offs were identified and mitigated early before the construction of the engine commenced.

see the paper >>>

Comparative Study of Distributed Consensus Gossip Algorithms for Network Size Estimation in Multi-Agent Systems
by Martin Kenyeres and Jozef Kenyeres
Abstract: Determining the network size is a critical process in numerous areas (e.g., computer science, logistic, epidemiology, social networking services, mathematical modeling, demography, etc.). However, many modern real-world systems are so extensive that measuring their size poses a serious challenge. Therefore, the algorithms for determining/estimating this parameter in an effective manner have been gaining popularity over the past decades. In the paper, we analyze five frequently applied distributed consensus gossip-based algorithms for network size estimation in multi-agent systems (namely, the Randomized gossip algorithm, the Geographic gossip algorithm, the Broadcast gossip algorithm, the Push-Sum protocol, and the Push-Pull protocol). We examine the performance of the mentioned algorithms with bounded execution over random geometric graphs by applying two metrics: the number of sent messages required for consensus achievement and the estimation precision quantified as the median deviation from the real value of the network size. The experimental part consists of two scenarios—the consensus achievement is conditioned by either the values of the inner states or the network size estimates—and, in both scenarios, either the best-connected or the worst-connected agent is chosen as the leader. The goal of this paper is to identify whether all the examined algorithms are applicable to estimating the network size, which algorithm provides the best performance, how the leader selection can affect the performance of the algorithms, and how to most effectively configure the applied stopping criterion.

see the paper >>>