SARL Community

You are welcome to provide a description of your work to appear on this page. Please update the Awesome SARL project, or submit an issue on the SARL web-site.

Scientific Publications using SARL

1. Manjah, D., Bary, T., Macq Benoı̂t, & Galland, S. (2025). Holonic Active Distillation for Scalable Multi-Agent Learning in Multi-Sensor Systems. 13th International Workshop on Engineering Multi-Agent Systems (EMAS-25), in International Conference on Autonomous Agents and Multiagent Systems (AAMAS-25).
   • Abstract
   • BibTeX

   The rapid expansion of sensor-based networks introduces major challenges in scalability, adaptability, and knowledge transfer, especially in open environments where new subsystems can dynamically join or leave. In this work, we propose a Holonic Active Distillation architecture within a Holonic Multi-Agent System (HMAS) to address these issues. Our approach integrates Clustered Stream-Based Active Distillation (CSBAD), a framework in which specialized student models collect local data, query pseudo-labels from teacher models, and cluster into groups of similar sensors. Results show that the holonic organization balances local specialization with global generalization, while efficiently adapting to sensor departures and re-integrations. We also analyzed trade-offs among incremental model updates, system reorganization, and scalability limits. Our findings highlight the advantages of holonic learning for multi-sensor systems while identifying key challenges related to model drift and long-term adaptation.

   @inproceedings{ConferencePaper_9514,
     title = {Holonic Active Distillation for Scalable {Multi-Agent} Learning in {Multi-Sensor} Systems},
     author = {Manjah, Dani and Bary, Tim and Macq, Beno{\^{\i}}t and Galland, St{\'{e}}phane},
     year = {2025},
     keywords = {Holonic Multi-Agent Systems; Distributed Learning; Collaborative Learning; Scalable Model Adaptation},
     booktitle = {13th International Workshop on Engineering Multi-Agent Systems (EMAS-25), in International Conference on Autonomous Agents and Multiagent Systems (AAMAS-25)},
     address = {Detroit, MI, USA},
     publisher = {IFAAMAS}
   }
   

2. Baldoni, M., Baroglio, C., and Galland, S., Micalizio, R., Outay, F., & Tedeschi, S. (2025). Protocoles d’interaction dans un langage de programmation orienté-agent impératif : le cas de BSPL et de SARL. Journées Francophones Sur Les Systèmes Multi-Agents (JFSMA-2025).
   • Abstract
   • BibTeX

   This article presents a framework for implementing BSPL interaction protocols within the agent-oriented programming language SARL. BSPL defines interaction protocols based on information flow, whereas SARL provides tools for constructing multi-agent systems. We introduce a set of transformation rules that enable the automatic generation of adapters, allowing SARL agents to execute protocols specified by BSPL. By aligning the declarative nature of BSPL with agent behaviors and the event-driven architecture of SARL, this approach facilitates the development of flexible, interaction-driven multi-agent systems. The auction protocol is used as an example to demonstrate the effectiveness of the integration presented in this article.

   @inproceedings{jfsma2025,
     author = {Baldoni, Matteo and Baroglio, Cristina and and Galland, St\'ephane and Micalizio, Roberto and Outay, Fatma and Tedeschi, Stefano},
     title = {Protocoles d'interaction dans un langage de programmation orient\'e-agent imp\'eratif : le cas de {BSPL} et de {SARL}},
     booktitle = {Journ\'ees Francophones sur les Syst\`emes Multi-agents (JFSMA-2025)},
     year = {2025},
     publisher = {\'Editions C\'epadu\`es},
     isbn = {9782383951940}
   }
   

3. Baldoni, M., Baroglio, C., Galland, S., Micalizio, R., Outay, F., & Tedeschi, S. (2025, May). Interaction Protocols in an Imperative Agent-Oriented Programming Language: the case of BSPL and SARL. 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-25).
   • Abstract
   • BibTeX

   This paper presents a framework for implementing BSPL interaction protocols in the SARL agent-oriented programming language. BSPL defines interaction protocols based on information flow, while SARL provides tools for building autonomous distributed systems. We introduce a set of transformation rules to automatically generate adapters, which allow SARL agents to enact BSPL-specified protocols with minimal manual effort required to agent developers. By aligning BSPL’s declarative nature with SARL’s agent behaviors and event-driven architecture, this approach facilitates the development of flexible, interaction-driven multi-agent systems. A practical example, the Contract Net Protocol, demonstrates the effectiveness of the presented integration.

   @inproceedings{aamas25,
     title = {Interaction Protocols in an Imperative {Agent-Oriented} Programming Language: the case of {BSPL} and {SARL}},
     author = {Baldoni, Matteo and Baroglio, Cristina and Galland, St{\'{e}}phane and Micalizio, Roberto and Outay, Fatma and Tedeschi, Stefano},
     year = {2025},
     month = may,
     keywords = {Interaction protocols, Engineering MAS, SARL, BSPL},
     booktitle = {24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-25)},
     address = {Detroit, MI, USA},
     publisher = {IFAAMAS}
   }
   

4. Mutambik, I. (2025). Sustainable IoT-Enabled Parking Management: A Multiagent Simulation Framework for Smart Urban Mobility. Sustainability, 17(14 (6382). https://doi.org/10.3390/su17146382
   • Abstract
   • BibTeX

   The efficient management of urban parking systems has emerged as a pivotal issue in today’s smart cities, where increasing vehicle populations strain limited parking infrastructure and challenge sustainable urban mobility. Aligned with the United Nations 2030 Agenda for Sustainable Development and the strategic goals of smart city planning, this study presents a sustainability-driven, multiagent simulation-based framework to model, analyze, and optimize smart parking dynamics in congested urban settings. The system architecture integrates ground-level IoT sensors installed in parking spaces, enabling real-time occupancy detection and communication with a centralized system using low-power wide-area communication protocols (LPWAN). This study introduces an intelligent parking guidance mechanism that dynamically directs drivers to the nearest available slots based on location, historical traffic flow, and predicted availability. To manage real-time data flow, the framework incorporates message queuing telemetry transport (MQTT) protocols and edge processing units for low-latency updates. A predictive algorithm, combining spatial data, usage patterns, and time-series forecasting, supports decision-making for future slot allocation and dynamic pricing policies. Field simulations, calibrated with sensor data in a representative high-density urban district, assess system performance under peak and off-peak conditions. A comparative evaluation against traditional first-come-first-served and static parking systems highlights significant gains: average parking search time is reduced by 42%, vehicular congestion near parking zones declines by 35%, and emissions from circling vehicles drop by 27%. The system also improves user satisfaction by enabling mobile app-based reservation and payment options. These findings contribute to broader sustainability goals by supporting efficient land use, reducing environmental impacts, and enhancing urban livability—key dimensions emphasized in sustainable smart city strategies. The proposed framework offers a scalable, interdisciplinary solution for urban planners and policymakers striving to design inclusive, resilient, and environmentally responsible urban mobility systems.

   @article{Sustainability2025,
     author = {Mutambik, Ibrahim},
     title = {Sustainable IoT-Enabled Parking Management: A Multiagent Simulation Framework for Smart Urban Mobility},
     journal = {Sustainability},
     volume = {17},
     year = {2025},
     number = {14 (6382)},
     url = {https://www.mdpi.com/2071-1050/17/14/6382},
     issn = {2071-1050},
     doi = {10.3390/su17146382}
   }
   

5. Rübel, P., Motsch, W., Bernhard, A., Jungbluth, S., & Ruskowski, M. (2025). Agent-Based Communication for Fault Diagnosis in Skill-Based Production Environments Using Messages Based on I4.0 Language and Asset Administration Shells. In K. Alexopoulos, S. Makris, & P. Stavropoulos (Eds.), Advances in Artificial Intelligence in Manufacturing II (pp. 157–170). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-86489-6_17
   • Abstract
   • BibTeX

   Small batch sizes and individualized products are managed with the concept of Cyber-Physical Production Systems (CPPS), enabling flexibility through interchangeable constellations, but increases complexity, especially when dealing with dependencies between decentralized subsystems. To increase the resilience and self-healing capabilities, greater automation of fault detection and diagnosis (FDD) is a key factor. It is a challenge to gather knowledge about faults, as these rarely occur compared to normal behavior. The flexibility in skill-based production systems makes this situation even more difficult. To overcome this challenge, data and knowledge about faults and their context from several Cyber-Physical Production Modules is used, which leads to federated knowledge databases. The knowledge databases are modeled in the Capability-Skill-Service-Fault-Symptom model (CSSFS model). To achieve the goal of high availability, resilience and autonomy of CPPS, automated decision-making for FDD using CSSFS applications is required. Therefore, automatic communication between FDD components is necessary. Therefore, focus of this paper is on the development of a communication scheme, which models participants using Asset Administration Shells and the I4.0 Language to model their interactions to enable automated communication and makes distributed knowledge accessible. To ensure decentralized control of these services, functionalities from several factory levels are encapsulated by Multi-Agent Systems (MAS) that follow a holonic structure.

   @inproceedings{Rubel2025,
     author = {R{\"u}bel, Pascal and Motsch, William and Bernhard, Alexis and Jungbluth, Simon and Ruskowski, Martin},
     editor = {Alexopoulos, Kosmas and Makris, Sotiris and Stavropoulos, Panagiotis},
     title = {Agent-Based Communication for Fault Diagnosis in Skill-Based Production Environments Using Messages Based on {I4.0} Language and Asset Administration Shells},
     booktitle = {Advances in Artificial Intelligence in Manufacturing II},
     month = mar,
     year = {2025},
     publisher = {Springer Nature Switzerland},
     address = {Cham},
     pages = {157--170},
     isbn = {978-3-031-86489-6},
     doi = {10.1007/978-3-031-86489-6_17}
   }
   

6. Bernhard, A. T., Jungbluth, S., Karnoub, A., Sidorenko, A., Motsch, W., Wagner, A., & Ruskowski, M. (2024). I4.0 Holonic Multi-agent Testbed Enabling Shared Production. In J. Soldatos (Ed.), Artificial Intelligence in Manufacturing: Enabling Intelligent, Flexible and Cost-Effective Production Through AI (pp. 231–250). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-46452-2_13
   • Abstract
   • BibTeX

   This chapter aims at presenting the system architecture of a distributed production testbed embedded in an interoperable Shared Production network. The goal of the modular architecture is to enable flexible, resilient and distributed production. The presented approach illustrates how Multi-Agent Systems (MAS) can be incorporated in the manufacturing domain for distributed components on different hierarchy layers based on a holonic approach. The concept is validated on the real-world demonstrator testbed of the SmartFactoryKL. Furthermore, the MAS is combined with Industry 4.0 technologies such as the Asset Administration Shell and OPC UA.

   @inbook{Bernhard2024,
     author = {Bernhard, Alexis T. and Jungbluth, Simon and Karnoub, Ali and Sidorenko, Aleksandr and Motsch, William and Wagner, Achim and Ruskowski, Martin},
     editor = {Soldatos, John},
     title = {{I4.0} Holonic Multi-agent Testbed Enabling Shared Production},
     booktitle = {Artificial Intelligence in Manufacturing: Enabling Intelligent, Flexible and Cost-Effective Production Through AI},
     year = {2024},
     publisher = {Springer Nature Switzerland},
     address = {Cham},
     pages = {231--250},
     isbn = {978-3-031-46452-2},
     doi = {10.1007/978-3-031-46452-2_13}
   }
   

7. Manjah, D., Galland, S., De Vleeschouwer, C., & Macq Benoı̂t. (2024, November). Architecture holonique pour la surveillance multi-capteur et multi-méthode du traffic routier au sein d’une ville intelligente. 32ème Journées Francophones Sur Les Systèmes Multi-Agents (JFSMA-24), in Plate-Forme Intelligence Artificielle (PFIA-24).
   • Abstract
   • BibTeX

   Cet article s’intéresse au déploiement de systèmes de surveillance flexibles et performants au sein de villes intelligentes. Ces systèmes doivent intégrer en continu de nouveaux capteurs et algorithmes de détection, qui sont autonomes (capables de prendre des décisions indépendamment d’un système central) et possèdent des compétences d’interaction (capables d’échanger des observations). À cet effet, notre travail propose d’adopter une architecture basée sur un modèle multi-agent organisationnel et holonique. Il tire parti de la modélisation hiérarchique du système et de méthodes autonomes de traitement des vidéos afin de créer des systèmes de surveillance multi-capteurs et multi-méthodes qui soient évolutifs et modulaires. Une étude de cas sur le suivi de véhicules montre la pertinence de notre approche en termes d’efficacité et de qualité de perception, ainsi que de temps d’exécution.

   @inproceedings{Manjah2024a,
     title = {Architecture holonique pour la surveillance multi-capteur et multi-m{\'{e}}thode du traffic routier au sein d'une ville intelligente},
     author = {Manjah, Dani and Galland, St{\'{e}}phane and De Vleeschouwer, Christophe and Macq, Beno{\^{\i}}t},
     year = {2024},
     month = nov,
     keywords = {Syst{\`{e}}me de surveillance multi-capteur et multi-m{\'{e}}thode, Holons, ASPECS, SARL},
     _language = {FRENCH},
     _publication_type = {NATIONAL_CONFERENCE_PAPER},
     _publication_type_name = {Papers in the proceedings of a national conference},
     _publication_category = {C_ACTN},
     _publication_category_name = {Papers in the proceedings of a national conference},
     booktitle = {32{\`{e}}me Journ{\'{e}}es Francophones sur les Syst{\`{e}}mes Multi-Agents (JFSMA-24), in Plate-Forme Intelligence Artificielle (PFIA-24)},
     address = {Carg{\`{e}}se, France},
     publisher = {Lavoisier}
   }
   

8. Manjah, D., Galland, S., De Vleeschouwer, C., & Macq Benoı̂t. (2024). Autonomous Methods in Multisensor Architecture for Smart Surveillance. 16th International Conference on Agents and Artificial Intelligence (ICAART-24), 3, 823–831. https://doi.org/10.5220/0012395700003636
   • Abstract
   • BibTeX

   This paper considers the deployment of flexible and high-performance surveillance systems. These systems must continuously integrate new sensors and sensing algorithms, which are autonomous (e.g., capable of making decisions independently of a central system) and possess interaction skills (e.g., capable of exchanging observations). For this purpose, our work proposes adopting an agent-based architecture derived from an organizational and holonic (i.e., system of systems) multi-agent model. It leverages autonomous processing methods, resulting in a scalable and modular multisensor and multimethod surveillance systems. A vehicle tracking case study demonstrates the relevance of our approach in terms of effectiveness and runtime.

   @inproceedings{Manjah2024b,
     title = {Autonomous Methods in Multisensor Architecture for Smart Surveillance},
     author = {Manjah, Dani and Galland, St{\'{e}}phane and De Vleeschouwer, Christophe and Macq, Beno{\^{\i}}t},
     year = {2024},
     month = feb,
     doi = {10.5220/0012395700003636},
     keywords = {Distributed Smart Cameras Architectures, Holonic Multiagent Systems, Large-scale Surveillance Systems, Multisensor and Multimethod},
     _language = {ENGLISH},
     _publication_type = {INTERNATIONAL_CONFERENCE_PAPER},
     _publication_type_name = {Papers in the proceedings of an international conference},
     _publication_category = {C_ACTI},
     _publication_category_name = {Papers in the proceedings of an international conference},
     booktitle = {16th International Conference on Agents and Artificial Intelligence (ICAART-24)},
     volume = {3},
     pages = {823--831},
     address = {Rome, Italy},
     _core_ranking = {B},
     publisher = {Springer},
     note = {CORE Ranking: B}
   }
   

9. Nour El Houda, D., Galland, S., Zakaria, T., Allaoua, N., & Ferkani, M. (2023). Distributed, Dynamic and Recursive Planning for Holonic Multi-Agent Systems: a behavioural model-based approach. Electronics, 12(23), 4797. https://doi.org/10.3390/electronics12234797
   • Abstract
   • BibTeX

   In this work, we propose a new distributed, dynamic, and recursive planning approach able to consider the hierarchical nature of the holonic agent and the unpredictable evolution of its behaviour. For each new version of the holonic agent, introduced because of the agent members obtaining new roles to achieve new goals and adapt to the changing environment, the approach generates a new plan that can solve the new planning problem associated with this new version against which the plans, executed by the holonic agent, become obsolete. To do this, the approach starts by generating sub-plans capable of solving the planning sub-problems associated with the groups of the holonic agent at its different levels. It then recursively links the sub-plans, according to their hierarchical and behavioural dependency, to obtain a global plan. To generate the sub-plans, the approach exploits the behavioural model of the holonic agent’s groups, thereby minimising the computation rate imposed by other multi-agent planning methods. In our work, we have used a concrete case to show and illustrate the usefulness of our approach.

   @article{NourElHouda2023,
     title = {Distributed, Dynamic and Recursive Planning for Holonic {Multi-Agent} Systems: a behavioural model-based approach},
     author = {Nour El Houda, Dehimi and Galland, St{\'{e}}phane and Zakaria, Tolba and Allaoua, Nora and Ferkani, Mouhamed},
     year = {2023},
     doi = {10.3390/electronics12234797},
     issn = {2079-9292},
     url = {https://www.mdpi.com/2079-9292/12/23/4797},
     keywords = {Automated Planning; Multi-agent planning (MAP); Distributed planning; Holonic multi-agent system HMAS; Unpredictable evolution of behaviour},
     _language = {ENGLISH},
     _publication_type = {INTERNATIONAL_JOURNAL_PAPER},
     _publication_type_name = {Articles in international journals with selection committee},
     _publication_category = {ACL},
     _publication_category_name = {Articles in international or national journals with selection committee and ranked in international databases},
     journal = {Electronics},
     publisher = {MDPI},
     address = {Switzerland},
     volume = {12},
     number = {23},
     pages = {4797},
     series = {Computer Science & Engineering - Special Issue on Collaborative Artificial Systems},
     _scimago_qindex = {Q2},
     _wos_qindex = {Q3},
     _impact_factor = {2.69},
     note = {Scimago Q-Index: Q2, WOS Q-Index: Q3, Impact factor: 2.69}
   }
   

10. Motsch, W., Simon, M., Sidorenko, A., Rübel, P., Kränzler, C., Wagner, A., & Ruskowski, M. (2023). Energy Agents for Energy Load Profiling in Modular Skill-Based Production Environments. In T. Borangiu, D. Trentesaux, P. Leitão, L. Berrah, & J.-F. Jimenez (Eds.), Service Oriented, Holonic and Multi-Agent Manufacturing Systems for Industry of the Future (SOHOMA 2023) (Vol. 1136, pp. 394–408). Springer Nature. https://doi.org/10.1007/978-3-031-53445-4_33
    • Abstract
    • BibTeX

    Modular skill-based production environments provide a high flexibility to fulfil various requirements in manufacturing like the production of individualized products or the selection of alternative production chains in case of unforeseen disturbances. Within these complex and changing production environments, there is a demand for transparency on the energy consumption and related energy costs for production processes, so that these can be considered during planning and monitoring of machine skills. However, the ability to manufacture products by using such flexible production processes leads to various constellations in which it is difficult to identify and map the related energy consumption of production skills. The objective of this paper is to develop a concept that, in the context of a multi-agent distributed production control system, allows energy agents to interact with resource agents to access energy metering data for energy load profiling during the skill execution in production. A special focus is put on how the functions of energy agents can support a methodical creation of energy load profiles on the granular level of skills. The realization and results are presented on a real-world demonstrator of the SmartFactory-KL as part of a skill-based production environment.

    @inproceedings{Sohoma2023,
      author = {Motsch, William and Simon, Marco and Sidorenko, Aleksandr and R{\"u}bel, Pascal and Kr{\"a}nzler, Christian and Wagner, Achim and Ruskowski, Martin},
      editor = {Borangiu, Theodor and Trentesaux, Damien and Leit{\~a}o, Paulo and Berrah, Lamia and Jimenez, Jose-Fernando},
      title = {Energy Agents for Energy Load Profiling in Modular Skill-Based Production Environments},
      booktitle = {Service Oriented, Holonic and Multi-Agent Manufacturing Systems for Industry of the Future (SOHOMA 2023)},
      year = {2023},
      volume = {1136},
      publisher = {Springer Nature},
      address = {Switzerland},
      pages = {394--408},
      isbn = {978-3-031-53445-4},
      doi = {10.1007/978-3-031-53445-4_33}
    }
    

11. Sidorenko, A., Motsch, W., Bekkum, M., van, Nikolakis, N., Alexopoulos, K., & Wagner, A. (2023). The MAS4AI framework for human-centered agile and smart manufacturing. Frontiers in Artificial Intelligence, 6(1241522). https://doi.org/10.3389/frai.2023.1241522
    • Abstract
    • BibTeX

    Volatility and uncertainty of today’s value chains along with the market’s demands for low-batch customized products mandate production systems to become smarter and more resilient, dynamically and even autonomously adapting to both external and internal disturbances. Such resilient behavior can be partially enabled by highly interconnected Cyber-Physical Production Systems (CPPS) incorporating advanced Artificial Intelligence (AI) technologies. Multi-agent solutions can provide better planning and control, improving flexibility and responsiveness in production systems. Small modular parts can autonomously take intelligent decisions and react to local events. The main goal of decentralization and interconnectivity is to enable autonomous and cooperative decision-making. Nevertheless, a more efficient orchestration of various AI components and deeper human integration are required. In addition, global behaviors of coalitions of autonomous agents are not easily comprehensible by workers. Furthermore, it is challenging to implement an Industry 4.0 paradigm where a human should be in charge of decision-making and execution. This paper discusses a Multi-Agent System (MAS) where several software agents cooperate with smart workers to enable a dynamic and reconfigurable production paradigm. Asset Administration Shell (AAS) submodels hold smart workers’ descriptions in machine-readable format, serving as an integration layer between various system’s components. The self-description capability of the AAS supports the system’s adaptability and self-configuration. The proposed concept supports the plug-and-produce functionality of the production modules and improves human-machine integration in the shared assembly tasks.
    

    @article{frai2023,
      author = {Sidorenko, Aleksandr and Motsch, William and Bekkum, van, Michael and Nikolakis, Nikolaos and Alexopoulos, Kosmas and Wagner, Achim},
      title = {The {MAS4AI} framework for human-centered agile and smart manufacturing},
      journal = {Frontiers in Artificial Intelligence},
      volume = {6},
      year = {2023},
      number = {1241522},
      issn = {2624-8212},
      doi = {10.3389/frai.2023.1241522},
      address = {Switzerland}
    }
    

12. Motsch, W., Wagner, A., & Ruskowski, M. (2024). Autonomous Agent-Based Adaptation of Energy-Optimized Production Schedules Using Extensive-Form Games. Sustainability, 16(9). https://doi.org/10.3390/su16093612
    • Abstract
    • BibTeX

    Modular cyber-physical production systems are an important paradigm of Industry 4.0 to react flexibly to changes. The flexibility of those systems is further increased with skill-based engineering and can be used to adapt to customer requirements or to adapt manufacturing to disturbances in supply chains. Further potential for application of these systems can be found in the topic of electrical energy supply, which is also characterized by fluctuations. The relevance of energy-optimized production schedules for manufacturing systems in general becomes more important with the increased use of renewable energies. Nevertheless, it is often difficult to adapt when short-term energy price updates or unforeseen events occur. To address these challenges with an autonomous approach, this contribution focuses on extensive-form games to adapt energy-optimized production schedules in an agent-based manner. The paper presents agent-based modeling to transform and monitor energy-optimized production schedules into game trees to respond to changing energy prices and disturbances in production. The game is setup with a scheduler agent and energy agents who are considered players. The implementation of the mechanism is presented in two use cases, realizing decision making for an energy price update in a simulation example and for unforeseen events in a real-world demonstrator.

    @article{sustainability2024,
      author = {Motsch, William and Wagner, Achim and Ruskowski, Martin},
      title = {Autonomous Agent-Based Adaptation of Energy-Optimized Production Schedules Using Extensive-Form Games},
      journal = {Sustainability},
      volume = {16},
      year = {2024},
      number = {9},
      article-number = {3612},
      url = {https://www.mdpi.com/2071-1050/16/9/3612},
      issn = {2071-1050},
      doi = {10.3390/su16093612}
    }
    

13. Wrona, Z., Buchwald, W., Ganzha, M., Paprzycki, M., Leon, F., Noor, N., & Pal, C.-V. (2023). Overview of Software Agent Platforms Available in 2023. Information, 14(6). https://doi.org/10.3390/info14060348
    • Abstract
    • BibTeX

    Agent-based computing remains an active field of research with the goal of building (semi-)autonomous software for dynamic ecosystems. Today, this task should be realized using dedicated, specialized frameworks. Over almost 40 years, multiple agent platforms have been developed. While many of them have been “abandoned”, others remain active, and new ones are constantly being released. This contribution presents a historical perspective on the domain and an up-to-date review of the existing agent platforms. It aims to serve as a reference point for anyone interested in developing agent systems. Therefore, the main characteristics of the included agent platforms are summarized, and selected links to projects where they have been used are provided. Furthermore, the described platforms are divided into general-purpose platforms and those targeting specific application domains. The focus of the contribution is on platforms that can be judged as being under active development. Information about “historical platforms” and platforms with an unclear status is included in a dedicated website accompanying this work.

    @article{Wrona2023,
      author = {Wrona, Zofia and Buchwald, Wojciech and Ganzha, Maria and Paprzycki, Marcin and Leon, Florin and Noor, Noman and Pal, Constantin-Valentin},
      title = {Overview of Software Agent Platforms Available in 2023},
      journal = {Information},
      volume = {14},
      year = {2023},
      number = {6},
      article-number = {348},
      url = {https://www.mdpi.com/2078-2489/14/6/348},
      issn = {2078-2489},
      doi = {10.3390/info14060348}
    }
    

14. Outay, F., Galland, S., Abbas-Turki, A., Martinet, T., Lombard, A., & Gaud, N. (2023). Addressing Hazardous Weather Conditions on Middle-East Highways with Smart Infrastructure and Connected Vehicles using Agent-Based Simulation. Personal and Ubiquitous Computing. https://doi.org/10.1007/s00779-023-01742-z
    • Abstract
    • BibTeX

    The lack of visibility due to foggy conditions is known to cause of a lot of accidents every year in the United Arab Emirates, eventually leading to fatal injuries. Yet, today’s technology can help to overcome these visibility issues by providing dynamic information to the driver about the current weather and an appropriate speed limit. This paper explores four strategies, ranging from static road signs to advanced inter-vehicular communication, to better warn the drivers and make them adapt their speed depending on the weather. To evaluate the impact of each policy, agent-based simulations are designed and performed. The results show that a dynamic communication about the weather conditions, supported by either an infrastructure-to-vehicle or a vehicle-to-vehicle protocol, can reduce the probability of occurrence of accidents.

    @article{pauc23,
      title = {Addressing Hazardous Weather Conditions on {Middle-East} Highways with Smart Infrastructure and Connected Vehicles using {Agent-Based} Simulation},
      author = {Outay, Fatma and Galland, St{\'{e}}phane and Abbas-Turki, Abdeljalil and Martinet, Thomas and Lombard, Alexandre and Gaud, Nicolas},
      year = {2023},
      doi = {10.1007/s00779-023-01742-z},
      issn = {1617-4917},
      keywords = {Agent-based Simulation; Microscopic simulation; Traffic Simulation; Foggy Weather Condition},
      journal = {Personal and Ubiquitous Computing},
      publisher = {Springer}
    }
    

15. Outay, F., Galland, S., Gaud, N., & Abbas-Turki, A. (2021). Simulation of Connected Driving in Hazardous Weather Conditions: General and Extensible Multiagent Architecture and Models. Int. Journal of Engineering Applications of Artificial Intelligence (EAAI), 104, 104412. https://doi.org/10.1016/j.engappai.2021.104412
    • Abstract
    • BibTeX

    Based on historical records, driving in hazardous weather conditions is one of the most serious causes that lead to fatal accidents on roads in general and in United Arab Emirates (UAE) highways in particular.  One solution for improving road safety is to equip the vehicles and infrastructure with connected and smart devices. Before deploying a concrete solution on the field,  it must be validated by simulation, and more specifically agent-based simulation.  Several key features are expected for the simulation framework, such as the reproduction of different and detailed behaviors for the components of the road infrastructure and for the drivers, simulate specific weather conditions and forecast their impacts on the global system behavior.  Additionally, several technological features are related to recent advancements in agent software engineering and simulation.   This  paper  proposes  an  agent-based  model  for  the  modeling  and simulation of traffic in foggy weather conditions that covers the above features and technological requirements.  The architecture is used and validated on two scenarios of traffic on UAE highways in foggy weather conditions.  The first scenario does not include an intelligent transport system, and the second considers smart speed limit panels.  From the experiments, the proposed model supports the expected key features,  i.e.,  microscopic simulation of intelligent transport systems,  including  infrastructure  and connected cars,  and of different  driving behaviors (human or autonomous car).  Even if the included weather condition model is basic,  a proof of concept is provided regarding the connection of an agent model and a weather condition model.

    @article{eaai2022a,
      keywords = {Agent-based Simulation, Microscopic simulation, Traffic Simulation, Foggy Weather Condition},
      note = {To be plublished},
      issn = {0952-1976},
      doi = {10.1016/j.engappai.2021.104412},
      url = {https://www.sciencedirect.com/science/article/pii/S0952197621002608},
      journal = {Int. Journal of Engineering Applications of Artificial Intelligence (EAAI)},
      volume = {104},
      pages = {104412},
      publisher = {Elsevier},
      month = aug,
      year = {2021},
      title = {Simulation of Connected Driving in Hazardous Weather Conditions: General and Extensible Multiagent Architecture and Models},
      author = {Outay, Fatma and Galland, St\'ephane and Gaud, Nicolas and Abbas-Turki, Abdeljalil}
    }
    

16. Multilevel and Holonic Model for Dynamic Holarchy Management: Application to Large-Scale Road Traffic. (2022). Int. Journal of Engineering Applications of Artificial Intelligence (EAAI), 109, 104622. https://doi.org/10.1016/j.engappai.2021.104622
    • Abstract
    • BibTeX

    Nowadays, with the emergence of connected objects and cars, road traffic systems become more and more complex and exhibit hierarchical behaviors at several levels of detail. The multilevel modeling approach is generally appropriate to represent traffic from several perspectives.  However, few works have been interested in  multilevel traffic modeling. Moreover, most of the available multilevel models of traffic proposed in the literature are static because they use a set of predefined levels of detail and these representations cannot change during simulation. To tackle these drawbacks, this paper introduces a holonic multilevel and dynamic traffic model for large-scale traffic systems. To this end, the paper proposes a density-based upward holonification model to group similar entities   to structure the holarchy of traffic. Additionally, it proposes a downward holonification model based on the Gaussian distribution   to  break down non-atomic entities. 
    Moreover, the paper presents a methodology for the management of the holarchy’s dynamics over time allowing the transitions between heterogeneous representations of a traffic system. Furthermore, multilevel indicators based on standard deviation are  proposed to assess the consistency of the simulation results. The experiments are conducted with several simple scenarios on a highway to investigate the trade-off between the simulation accuracy and the availability of computational resources.

    @article{eaai2022b,
      keywords = {Holonic Multiagent System, Multilevel Modeling and Simulation, Large-Scale Road Traffic, DBSCAN, Intelligent Driver Model},
      issn = {0952-1976},
      doi = {10.1016/j.engappai.2021.104622},
      language = {English},
      journal = {Int. Journal of Engineering Applications of Artificial Intelligence (EAAI)},
      volume = {109},
      pages = {104622},
      month = feb,
      year = {2022},
      title = {Multilevel and Holonic Model for Dynamic Holarchy Management: Application to Large-Scale Road Traffic},
      author = {}
    }
    

17. Outay, F., Abbas-Turki, A., Galland, S., Lombard, A., & Gaud, N. (2022). Comparison of Reaction Time-based Collaborative Velocity Control and Intelligent Driver Model for Agent-based Simulation of Autonomous Car . Elsevier.
    • Abstract
    • BibTeX

    Based on historical records, driving in hazardous weather conditions is one of the most serious causes that lead to fatal accidents
    on roads in general and in United Arab Emirates (UAE) highways in particular. One solution to improve road safety is to equip
    vehicles and infrastructure with connected and smart devices and to convert them to autonomous vehicles. Before deploying a
    concrete solution to the field, it must be validated by simulation, and more specifically, agent-based simulation. In this paper,
    we propose to implement the Reaction Time-Based Collaborative Velocity Control (RT-CVC) model that was implemented in
    autonomous cars into an agent-based simulator. This model is compared to the Intelligent Driver Model (IDM) , which is one of
    the standard longitudinal driving behaviors in simulation environments. Experimental results show that RT-CVC provides higher
    results regarding safety and fluidity of traffic. This positive analysis is balanced by the fact that RT-CVC is designed for autonomous
    cars and IDM is designed to model human-drive decisions. Using RT-CVC for modeling a human driver may be counter productive
    in simulation experiments.

    @inproceedings{mobispc2022b,
      keywords = {Driving model, Microsimulation, Agent-oriented model, Comparison},
      pages = {Elsevier},
      organization = {Acadia University and Hasselt University},
      publisher = {Niagara Falls, Ontario, Canada},
      address = {19th International Conference on Mobile Systems and Pervasive Computing},
      month = aug,
      year = {2022},
      title = {Comparison of Reaction Time-based Collaborative Velocity Control and Intelligent Driver Model for Agent-based Simulation of Autonomous Car },
      author = {Outay, Fatma and Abbas-Turki, Abdeljalil and Galland, St\'ephane and Lombard, Alexandre and Gaud, Nicolas}
    }
    

18. Tchappi Haman, I., Etienne Ndamlabin Mboula, J., Najjar, A., Mualla, Y., & Galland, S. (2022, September). A Decentralized Multilevel Agent Based Explainable Model for Fleet Management of Remote Drones. 19th International Conference on Mobile Systems and Pervasive Computing.
    • Abstract
    • BibTeX

    With the widespread use of artificial intelligence, understanding the behavior of intelligent agents and robots such as drones is
    crucial to guarantee successful human-agent interaction since it is not straightforward for humans to understand an agent?s state of
    mind. Recent empirical studies have confirmed that explaining a system?s behavior to human users fosters the latter?s acceptance of
    the system and therefore bring out the importance of explainability. However, providing overwhelming or sometimes unnecessary
    information may also confuse the users and cause failure. For these reasons, this paper proposes a decentralized method to aggregate
    explanations sent by remote agents to human users according to the user?s wishes and needs. To this end, the paper relies on holonic
    multiagent system in order to decompose hierarchically environment and enable the aggregation of the explanations. The proposal
    is tested on a small scenario and outlines explanations at different levels of detail from microscopic to macroscopic.

    @inproceedings{mobispc2022a,
      keywords = {Drones, eXplainable Artificial Intelligence, Holonic MultiAgent System, Decentralized approach},
      publisher = {Elsevier},
      organization = {Acadia University and Hasselt University},
      address = {Niagara Falls, Ontario, Canada},
      booktitle = {19th International Conference on Mobile Systems and Pervasive Computing},
      month = sep,
      year = {2022},
      title = {A Decentralized Multilevel Agent Based Explainable Model for Fleet Management of Remote Drones},
      author = {Tchappi Haman, Igor and Etienne Ndamlabin Mboula, Jean and Najjar, Amro and Mualla, Yazan and Galland, St\'ephane}
    }
    

19. ZHAO, H., MUALLA, Y., GALLAND, S., TCHAPPI HAMAN, I., BELLEMANS, T., & YASAR, A.-U.-H. (2020, May). Decision-Making under Time Pressure when Rescheduling Daily Activities. 11th International Conference on Ambient Systems, Networks and Technologies (ANT20).
    • Abstract
    • BibTeX

    Generally during the execution of the daily schedule, there is a mismatch between the plan and the reality. Faced with unexpected events, which affect the schedule, individuals need to reschedule their decisions. In such situations, time is an important factor when making a rescheduling decision, as people feel time pressure because of the time threshold. Consequently, the rescheduling decision is made under the individual’s own Perceived Time Pressure (PTP). PTP does not only depend on the actual time pressure, but also on the individual’s characteristics. The aim of this paper is to establish a model to simulate the individual decision behavior under PTP. Under different levels of PTP, individuals will choose different strategies to take the decision, and there are three decision strategies to consider: optimal, salient and experience.

    @inproceedings{ant2020,
      booktitle = {11th International Conference on Ambient Systems, Networks and Technologies (ANT20)},
      keywords = {Perceived Time Pressure, Decision Strategy, Individual Decision Model, Task Complexity, Choice Probability, Activity Rescheduling},
      month = may,
      year = {2020},
      address = {Warsaw, Poland},
      title = {Decision-Making under Time Pressure when Rescheduling Daily Activities},
      author = {ZHAO, Hui and MUALLA, Yazan and GALLAND, St\'ephane and TCHAPPI HAMAN, Igor and BELLEMANS, Tom and YASAR, Ansar-Ul-Haque}
    }
    

20. LOMBARD, L., Alexandre an DURAND, & GALLAND, S. (2020, May). Velocity Obstacle Based Strategy for Multi-agent Collision Avoidance of Unmanned Aerial Vehicles. 2nd International Workshop on Internet of Autonomous Unmanned Vehicles (IAUV20).
    • Abstract
    • BibTeX

    Unmanned Aerials Vehicles (UAVs), most known as drones, recently gained a lot of interest in several domains of civil applications. With the number of operating drones expected to quickly rise in the next few years comes the need to develop efficient collision avoidance solutions. To ensure the applicability of the collision avoidance solutions, given the limitations of UAVs, they must rely on a reliable source of information, and must be computationally efficient. This paper aims at providing an implementation of the Velocity Obstacle collision avoidance method, based on the information transmitted by the other UAVs. Multi-agent based simulations using the simulation software AirSim and the multi-agent platform SARL are proposed to assess the validity of the proposed solution.

    @inproceedings{sarl2020,
      booktitle = {2nd International Workshop on Internet of Autonomous Unmanned Vehicles (IAUV20)},
      keywords = {Unmanned aerial vehicles, collision avoidance, multi-agent systems},
      month = may,
      year = {2020},
      title = {Velocity Obstacle Based Strategy for Multi-agent Collision Avoidance of Unmanned Aerial Vehicles},
      author = {LOMBARD, Alexandre an DURAND, Lilian and GALLAND, St\'ephane}
    }
    

21. NGOUNOU NTOUKAM, E. D., KAMGANG, J.-C., KAMLA, V. C., MUALLA, Y., TCHAPPI HAMAN, I., GALLAND, S., & EMVUDU WONO, Y. S. (2020, May). Agent-Based Model of Cocoa Mirids at the Scale of a Cocoa Farm. 4th International Workshop on Agent-Based Modeling and Applications with SARL (SARL-20), Procedia Computer Science.
    • Abstract
    • BibTeX

    Cocoa beans are vital for the chocolate industries, with some African countries (Ivory Coast, Ghana, Nigeria and Cameroon) currently having 72% of the worldwide cocoa production. However, cocoa cultivation faces many threats such as diseases and insects. The most damaging insect that attacks cocoa plant in West Africa is the mirid. The previous works on the mirids accentuate their attention on the macroscopic view of the mirids. Considering the complexity of the environment where mirids live, it is difficult to properly understand the mirids’ dynamics without considering the individual behaviors of the mirids population. The representation of the mirids’ dynamics enables the ability to test many use-case scenarios. To this end, Multi-agent Systems are a suitable paradigm to model complex systems bringing out the interactions between individuals and their environment, along with the impact of their behavior. Therefore, we propose in this paper an agent-based model of the mirids’ dynamics in a cocoa farm. To build this model, we rely on the Agent-oriented Software Process for Engineering Complex Systems (ASPECS) process.

    @inproceedings{sarl2021,
      booktitle = {4th International Workshop on Agent-based Modeling and Applications with SARL (SARL-20), Procedia Computer Science},
      keywords = {Mirid; Agent-based modeling; Cocoa tree; ASPECS process},
      month = may,
      publisher = {Elsevier},
      year = {2020},
      title = {Agent-Based Model of Cocoa Mirids at the Scale of a Cocoa Farm},
      author = {NGOUNOU NTOUKAM, Emmanuel Dimitry and KAMGANG, Jean-Claude and KAMLA, Vivient Corneille and MUALLA, Yazan and TCHAPPI HAMAN, Igor and GALLAND, St\'ephane and EMVUDU WONO, Yves S\'ebastien}
    }
    

22. Modèle dynamique et multiniveau holonique basé sur la densité: application au trafic routier à grande échelle. (2019). Journées Francophones Sur Les Systèmes Multiagents (JFSMA19), Toulouse, France, 136–145. https://www.irit.fr/pfia2019/jfsma/
    • Abstract
    • BibTeX

    De nos jours, avec l’émergence d’objets et de voitures connectés, les systèmes de trafic deviennent de plus en plus complexes et présentent des comportements hiérarchiques à plusieurs niveaux d’observation. La plupart des modèles de simulation multiniveaux utilisent un ensemble de niveaux prédéfinis. La commutation dynamique des niveaux lors de l’exécution de la simulation permet d’adapter le modèle aux contraintes liées à la qualité des résultats ou aux ressources de calcul disponibles. Cet article présente un nouveau modèle multiniveau basé sur la densité pour la gestion dynamique d’une holarchie représentant un système de trafic. La proposition étend l’algorithme DBSCAN dans le contexte des systèmes multi-agents holonique. Une méthode de commutation dynamique entre les différents niveaux d’abstractions est proposée. À cette fin, des indicateurs multiniveaux basés sur l’écart type sont proposés afin d’évaluer la cohérence des résultats de la simulation. Le modèle proposé est testé avec le modèle de poursuite de voiture Intelligent Driver Model.

    @inproceedings{jfsma2019,
      address = {Toulouse, France},
      booktitle = {Journ{\'e}es Francophones sur les Syst{\`e}mes Multiagents (JFSMA19), Toulouse, France},
      keywords = {Syst{\`e}me MultiAgent Holonique, Mod{\'e}lisation et simulation multiniveau, DBSCAN, Trafic},
      language = {french},
      month = jul,
      organization = {PFIA-19},
      pages = {136-145},
      publisher = {Association Francaise d'Intelligence Artificielle},
      url = {https://www.irit.fr/pfia2019/jfsma/},
      year = {2019},
      title = {Mod{\`e}le dynamique et multiniveau holonique bas{\'e} sur la densit{\'e}: application au trafic routier {\`a} grande {\'e}chelle},
      author = {}
    }
    

23. Holonification Model for a Multilevel Agent-based System. Application to Road Traffic. (2018). Int. Journal of Personal and Ubiquitous Computing.
    • Abstract
    • BibTeX

    Organizational models and holonic multi-agent systems are growing as a powerful tool for modeling and developing large-scale complex system. The main issue in deploying holonic multiagent systems is the building of the holonic model called holarchy. This paper presents a novel density approach to cluster and hierarchize population in order to build the initial holarchy. The proposal extends DBSCAN algorithm. Moreover, multilevel indicators based on standard deviation are proposed in order to evaluate the consistency of the holonification process. The proposed model is tested in a road traffic modeling in order to build the initial holarchy. The paper presents also the main research direction towards the control of internal and external stimuli of traffic over time.

    @article{ijpuc2018,
      journal = {Int. Journal of Personal and Ubiquitous Computing},
      keywords = {DBSCAN, Holonic Multiagent System, Road Traffic, Multilevel Model, Initial Holarchy},
      language = {english},
      month = dec,
      publisher = {Springer},
      year = {2018},
      title = {Holonification Model for a Multilevel Agent-based System. Application to Road Traffic},
      author = {}
    }
    

24. Holonification of Road Traffic based on Graph Theory. (2018, September). 13th International Conference Cellular Automata for Research and Industry (ACRI18), the 5th Workshop on Traffic and Cellular Automata (TCA18).
    • Abstract
    • BibTeX

    Organizational models and holonic multi-agent systems are growing as a powerful tool for modeling and developing large-scale com- plex system. The main issue in deploying holonic multiagent systems is the building of the holonic model called holarchy. This paper presents a novel top down approach based on graph theory in order to build recur- sively the initial holarchy of road traffic. Moreover, multilevel indicators based on standard deviation is proposed in order to evaluate the consis- tency of the holonification process.

    @inproceedings{acri2018,
      booktitle = {13th International Conference Cellular Automata for Research and Industry (ACRI18), the 5th Workshop on Traffic and Cellular Automata (TCA18)},
      keywords = {Graph theory; Holonic Multiagent System; Road Traffic; Multi- level Model},
      language = {english},
      month = sep,
      note = {Lectures Notes in Computer Science},
      year = {2018},
      title = {Holonification of Road Traffic based on Graph Theory},
      author = {}
    }
    

25. Tchappi Haman, I., Kamla, V. corneille, Galland, S., & Kamgang, J.-C. (2017, February). Towards an Multilevel Agent-based Model for Traffic Simulation. The 6th International Workshop on Agent-Based Mobility, Traffic and Transportation Models, Methodologies and Applications (ABMTRANS’17).
    • Abstract
    • BibTeX

    Large scale road traffic is a complex system that could be modelled with a multilevel approach. Most of the multilevel models from the literature have fixed a priori level of details (micro-meso, micro- macro, meso-macro). This paper has two goals: it presents the state of the art related to large scale traffic models, and it gives the main research direction to create a novel multilevel model that support dynamic selection of the level during the simulation. Our proposal is based on an organizational modelling approach and the use of the concept of holon (agent composed of agents).

    @inproceedings{abmtrans17,
      booktitle = {the 6th International Workshop on Agent-based Mobility, Traffic and Transportation Models, Methodologies and Applications (ABMTRANS'17)},
      keywords = {agent based modeling, large scale, traffic, organisational model, multilevel model, holon},
      language = {english},
      month = feb,
      publisher = {Springer},
      year = {2017},
      title = {Towards an Multilevel Agent-based Model for Traffic Simulation},
      author = {Tchappi Haman, Igor and Kamla, Vivient corneille and Galland, St{\'e}phane and Kamgang, Jean-Claude}
    }
    

26. Cich, G., Knapen, L., Maciejewski, A.-U.-H., Michał Yasar, Bellemans, T., & Janssens, D. (2017, May). Modeling Demand Responsive Transport using SARL and MATSim. International Workshop on Agent-Based Modeling and Applications with SARL (SARL 2017).
    • BibTeX

    @inproceedings{sarlws17b,
      booktitle = {International Workshop on Agent-based Modeling and Applications with SARL (SARL 2017)},
      language = {english},
      month = may,
      publisher = {Elsevier},
      year = {2017},
      title = {Modeling Demand Responsive Transport using SARL and MATSim},
      author = {Cich, Glenn and Knapen, Luk and Maciejewski, Michał Yasar, Ansar-Ul-Haque and Bellemans, Tom and Janssens, Davy}
    }
    

27. Cich, G., Knapen, L., Galland, S., Vuurstaek, J., Neven, A., & Bellemans, T. (2016, February). Towards an Agent-based Model for Demand-Responsive Transport Serving Thin Flows. The 5th International Workshop on Agent-Based Mobility, Traffic and Transportation Models, Methodologies and Applications (ABMTRANS 2016).
    • Abstract
    • BibTeX

    Low volume traveler flows cause problems for public transportation (PT) providers. The Smart- PT project aims to find out how such flows can be combined to increase the service provider viability. The capability to conceive multi-modal trips is fundamental in that context and is modeled by the Trip Sequence Composer (TSC) concept. A TSC is an essential component of the traveler’s brain, of the customer support operated by collective transport providers, of trip advisers in websites etc. We present a simulation model design to evaluate the effect of cooperating TSCs on the viability of demand responsive collective transport providers. While obeying specific regulations, specialized services targeting mobility impaired people can also serve regular requests in order to save fleet and personnel costs.

    @inproceedings{abmtrans16,
      booktitle = {the 5th International Workshop on Agent-based Mobility, Traffic and Transportation Models, Methodologies and Applications (ABMTRANS 2016)},
      keywords = {Demand-Responsive Transport, Thin Flows, Micro- Simulation, Agent-Based Modeling, Organizational Modeling},
      language = {english},
      month = feb,
      publisher = {Procedia Computer Science, Elsevier},
      year = {2016},
      title = {Towards an Agent-based Model for Demand-Responsive Transport Serving Thin Flows},
      author = {Cich, Glenn and Knapen, Luk and Galland, St{\'e}phane and Vuurstaek, Jan and Neven, An and Bellemans, Tom}
    }