EASSS 2026

 EASSS 2026 (26ª edizione) — 21–23 settembre 2026, Malmö University, Svezia. Pagina del sito: quattro tutorial, una giornata condivisa con EUMAS 2026 e una keynote congiunta di Ann Nowé; comitato organizzatore Nosheen Abid e Harko Verhagen. Edizione forthcoming al momento del recupero.
Recovered 2026-09-14 by Claude for the APICe Event record.
Source: https://euramas.github.io/easss2026/

------------------------------------------------------------------------

EASSS 2026 MAIN CSS --> EASSS 2026 About Call for Tutorials Registration Programme Colocated Events --> Local Information Committee --> EASSS 2026 The 26th European Agent Systems Summer School September 21-23, 2026 | Malmö, Sweden EASSS 2026 The 26th European Agent Systems Summer School September 21-23, 2026 | Malmö, Sweden EASSS 2026 The 26th European Agent Systems Summer School September 21-23, 2026 | Malmö, Sweden Three days of tutorials and networking, featuring four tutorials by international experts and a shared day with EUMAS 2026, including a keynote by Prof. Ann Nowé (Vrije Universiteit Brussel). Explore the detailed programme here . The registration for EUMAS2026 and EASSS2026 is now open: Register here by July 24 for Early Bird discount. We offer a discounted registration fee if you attend both events. The registration process is hosted by Invajo, conference fees will be charged in Swedish krona (SEK), and you can pay by credit card. About The 26th European Agent Systems Summer School (EASSS 2026) will take place at Malmö University , Sweden, on 21–23 September 2026 , under the auspices of EURAMAS , the European Association for Multi-Agent Systems. EASSS 2026 is hosted by the Department of Computer Science and Media Technology (DVMT) and the Sustainable Digitalisation Research Centre (SDRC) at Malmö University. Since it began in 1999, EASSS has grown into one of the key meeting points in Europe for people working on autonomous agents and multi-agent systems, bringing together experienced researchers and early-career scientists in a focused, collaborative setting. The program is designed for advanced Master’s students, PhD candidates, and early-career researchers, offering tutorials led by experts that balance core foundations with the latest developments shaping the field. Topics span both theory and real-world applications of distributed intelligent systems, from the Internet of Things and autonomous robotics to smart environments and large-scale AI systems, reflecting where the field is heading and where it is already making impact. Important Dates Tutorial Proposals: 10 May 2024 (AoE, UTC-12) --> 25 May 2026 (AoE, UTC-12) Early Bird Registration: 31 July 2024 (AoE, UTC-12) --> until 24 July 2026 Summer School: 21-23 September 2026 Call For Tutorials The Organizing Committee of the 26th European Agent Systems Summer School (EASSS 2026) invites tutorial proposals for the event to be held at Malmö University , Sweden, on 21–22 September 2026 . We are looking for engaging, well-structured tutorials that introduce key ideas in Autonomous Agents and Multi-Agent Systems while also highlighting emerging directions shaping the field today. Topics aligned with communities such as AAMAS and the JAAMAS journal are especially relevant. Tutorials should provide a clear and balanced perspective on a topic, combining conceptual understanding with practical insight and real-world relevance. Each tutorial will run for approximately 3 hours (typically split into two 90-minute sessions) and is usually delivered by one or two instructors. We welcome contributions from both experienced researchers and early-career academics, aiming to create an interactive and high-quality learning experience for participants. A contribution towards travel and accommodation may be provided for accepted tutorials. Submission Instructions Tutorial proposals must be submitted as a single PDF document (maximum 2 pages ) using the official LaTeX template . Proposals should clearly communicate both the academic value and the learning experience of the tutorial. The expected structure follows established EASSS guidelines. Duration (standard: 3 hours; justify deviations) Equipment requirements Short bios (~100 words per tutor) Relevant teaching experience Tutorial Objectives Introduce key areas of AAMAS research Provide depth in established methodologies and techniques Survey and critically assess mature or emerging topics Motivate and position new research directions Support hands-on understanding through practical or coding sessions Bridge research with real-world and industry applications Tutorial Format Duration: 3 hours (two sessions of 90 minutes) Format: lecture, interactive, or hands-on Tutors: typically 1–2 presenters (larger teams must justify coherence) Tutorials should be designed to engage a diverse audience, from advanced students to researchers entering a new area. Scope and Topics We welcome proposals across the full spectrum of Autonomous Agents and Multi-Agent Systems, including (but not limited to): Foundations of multi-agent systems Reinforcement learning and decision-making Coordination, organizations, norms, and ethics Agent-based modelling and simulation Human-agent interaction and human-in-the-loop systems Trustworthy and explainable agentic AI Multi-agent learning and collective intelligence LLM-based agents and hybrid architectures Applications in robotics, healthcare, sustainability, and industry We particularly encourage tutorials that connect established MAS principles with emerging paradigms, emphasize real-world impact, and include interactive or hands-on components. Evaluation Criteria Relevance and timeliness of the topic Clarity and pedagogical quality Expected interest for the EASSS audience Expertise and experience of the tutors Support A limited number of accepted tutorials may receive partial travel and accommodation support (up to €500), subject to budget availability. There is no registration fee for attending the summer school. Submission Proposals should be submitted via OpenReview (submission link to be announced). Contact For any questions, please contact: easss2026@mau.se Registration Registration for EASSS 2026 is now open. Registration is handled externally by Invajo , our conference registration and payment provider. Register for EUMAS 2026 Attendance Student Fee (including PhD students) Non-Student Fee (researchers and industry) Early Bird (until July 24) Late (from July 25) Early Bird (until July 24) Late (from July 25) EASSS (Summer School) 250€ 300€ 280€ 340€ EUMAS (Main Conference) 300€ 360€ 350€ 420€ Both EASSS and EUMAS 500€ 600€ 600€ 720€ The registration fees are displayed in EUR for convenience only. Payments will be charged in SEK (Swedish krona) and may vary at the time of payment. A discount applies if you register for both EASSS and EUMAS (see table above). Registration Policy Registration fees are charged in Swedish krona (SEK) and can be paid by credit card . Invoice payment is available for organizations with a valid VAT number . For every accepted paper, at least one author must register by the early bird deadline ( July 24 ). Registration fees are non-refundable . However, a registration can be transferred to a colleague — please use the contact details provided on the registration system to update the participant details. Visa Information If you require an official invitation letter to support a visa application, please contact the Organizing Committee at eumas2026@mau.se . EUMAS (Main Conference): Invitation letters can only be issued to authors of an accepted paper . We are unable to issue invitation letters to participants without an accepted submission. EASSS (Summer School): Participants who require an invitation letter are requested to contact the organizers before registering . Invitation letters are issued only once registration is fully completed and the registration fee has been paid in full, at the discretion of the EASSS Chairs. Please note that registration fees are non-refundable, including in the case of visa refusal, so please only register if you genuinely intend to attend. Please contact us well in advance of the conference to allow sufficient time for visa processing. EASSS2026 Program EASSS2026 will take place on Monday + Tuesday, Sep 21-22, 2026, as part of the pre-conference program of EUMAS2026, which will take place Wednesday - Friday, Sept 23-25, 2026. The Summer School will consist of a three day program, consisting of different tutorials as well as an overlap with the EUMAS conference, which gives participants the possibility to attend keynote lectures. Schedule EASSS - Summer School (26th European Agent Systems Summer School) EUMAS - Main Conference (23rd European Conference on Multi-Agent Systems) Time Monday Sept 21 Tuesday Sept 22 Wednesday Sept 23 Thursday Sept 24 Friday Sept 25 09:00–10:30 From Micro-Behaviors to Macro-Phenomena: An Introduction to Agent-Based Modeling Multiagent Reinforcement Learning (MARL) for Traffic Control Opening Session Keynote: Ann Nowé Demo pitches Keynote: Carles Sierra Demo pitches Paper Session 6 Main conference track 10:30–11:00 Coffee Break Coffee Break Coffee Break (with Demos) Coffee Break (with Demos) Coffee Break 11:00–12:30 From Micro-Behaviors to Macro-Phenomena: An Introduction to Agent-Based Modeling (continued) Multiagent Reinforcement Learning (MARL) for Traffic Control (continued) Paper Session 1 Research presentations Paper Session 4 Research presentations Paper Session 7 Research presentations 13:00–14:00 Lunch Lunch Lunch Lunch Lunch 14:00–15:30 Formal Methods for Safe Reinforcement Learning Multiagentic AI: Engineering Safe and Flexible Systems Paper Session 2 Research presentations Paper Session 5 Research presentations Paper Session 8 Research presentations Closing Session 15:30–16:00 Coffee Break Coffee Break Coffee Break (with Demos) Coffee Break (with Demos) Coffee Break 16:00–17:30 Formal Methods for Safe Reinforcement Learning (continued) Multiagentic AI: Engineering Safe and Flexible Systems (continued) Paper Session 3 Research presentations EURAMAS General Assembly Annual meeting 17:30–19:00 Welcome Reception Conference Dinner From Micro-Behaviors to Macro-Phenomena: An Introduction to Agent-Based Modeling Tutors: Sz-Ting (Christine) Tzeng and Bertilla Fabris, Umeå University, Sweden. Abstract This tutorial introduces agent-based modeling (ABM) as a practical and theoretical approach for studying how complex macro-level phenomena emerge from the local behavior and interactions of individual agents. Participants will learn the core ideas behind ABM, including agent heterogeneity, local interaction rules, adaptation, emergence, and the use of simulation for understanding social systems and supporting policy design. The tutorial also clarifies that, in ABM, an “agent” refers broadly to an autonomous entity in a model, not necessarily to an LLM-based or generative AI system. The session combines short lectures with hands-on group work in NetLogo. Participants will explore classic models such as Wolf Sheep Predation and Schelling segregation, examine hidden states and policy interventions using the Virus model, and then frame or adapt an ABM for a problem of interest such as healthcare, traffic, misinformation, resource allocation, or housing. The tutorial is designed to be accessible to participants with different levels of programming experience. Tutor Bios Sz-Ting (Christine) Tzeng Sz-Ting (Christine) Tzeng is a postdoctoral researcher in the Socially Aware AI research group at Umeå University. Her research focuses on multi-agent systems, explainable AI, and human-centered AI, with particular attention to value alignment, human-in-the-loop perspectives, human factors, and adaptive AI systems aligned with human norms and values. Bertilla Fabris Bertilla Fabris is a PhD student at Umeå University. Their research focuses on agent-based social simulation for critical healthcare processes, with an emphasis on using simulation models to understand complex social and organizational dynamics in healthcare settings. Multiagent Reinforcement Learning (MARL) for Traffic Control Tutor: Ana Lúcia Cetertich Bazzan, University of São Paulo, Polytechnic School, Brazil. Abstract This tutorial presents traffic control as a major application area for multi-agent systems and multiagent reinforcement learning. It begins with an introduction to traffic control, including traffic signal control, and gives a brief historical overview of classical and AI-based techniques. The tutorial then introduces key MARL concepts, including multiobjective MARL and the challenges caused by non-stationarity in traffic environments. The main part of the tutorial explains how MARL can be applied to traffic control problems involving vehicles, pedestrians, public transportation, emissions, and competing objectives. Participants will see how MARL-based traffic control can be implemented step by step using the SUMO microscopic traffic simulator. The tutorial concludes by discussing the current state of the field and future directions for the MAS research agenda in transportation. Tutor Bio Ana Lúcia Cetertich Bazzan Ana Lúcia Cetertich Bazzan’s PhD research focused on reinforcement learning and game-theoretic approaches to traffic signal control. From 1999 to 2024, she was a professor at UFRGS, where she led the MAS group, and she continues there as a visiting professor. Since June 2026, she has also been a visiting professor at the Department of Transportation at the University of São Paulo. She is a recognized expert on agents, MARL, and traffic control, and has served the AAMAS community, including as general co-chair of AAMAS 2014. Formal Methods for Safe Reinforcement Learning Tutors: Francesco Belardinelli and Omar Adalat, Imperial College London, United Kingdom. Abstract This tutorial presents the emerging connection between reinforcement learning and formal methods, focusing on how verification techniques can support the development of safe, reliable, and trustworthy AI systems. It introduces the basics of reinforcement learning and constrained reinforcement learning, then explains why some temporal objectives and safety requirements cannot be fully captured by standard constrained RL formulations. Participants will be introduced to Linear Temporal Logic (LTL), automata-based specification, model checking, and synthesis, and will learn how these tools can be used to design RL algorithms with formal objectives, constraints, and safety guarantees. The tutorial covers state-of-the-art methods such as constrained MDPs and shielding, and uses examples from robot motion planning, water-tank control, and game-playing agents such as Pac-Man to illustrate the main ideas. Tutor Bios Francesco Belardinelli Francesco Belardinelli is a Senior Lecturer in the Department of Computing at Imperial College London, where he leads the Formal Methods in AI lab. He has led multiple research projects and co-authored more than 100 conference and journal papers on the theoretical foundations and applications of formal methods for specifying and verifying complex AI systems. His recent work focuses on safe reinforcement learning. Omar Adalat Omar Adalat is a PhD student in the Department of Computing at Imperial College London. His research focuses on safe multi-agent learning with probabilistic and quantitative temporal logic constraints, as well as learning from formal specifications. He has served as a teaching assistant for modules including Formal Methods in AI, Deep Learning, Introduction to Symbolic AI, and Reinforcement Learning. Multiagentic AI: Engineering Safe and Flexible Systems Tutors: Amit K. Chopra, Lancaster University, United Kingdom; Munindar P. Singh, North Carolina State University, USA. Abstract This tutorial studies Agentic AI through the lens of multi-agent systems. It examines how agentic approaches support interactions among autonomous agents and contrasts them with declarative approaches based on interaction protocols and norms. The tutorial focuses on how flexible and safe interactions can be engineered by combining agentic systems with formally specified interaction models. Topics include the motivations and applications of Agentic AI, emerging industry-backed interaction protocols, declarative interaction protocols, LLM agents that enact protocols without protocol-specific programming, and norms-based decision making. By the end of the tutorial, participants will be able to critically assess Agentic AI approaches and understand how multi-agent system concepts, protocols, norms, and software tools can help address their limitations. Tutor Bios Amit K. Chopra Amit K. Chopra is a Senior Lecturer at Lancaster University. His expertise lies in engineering abstractions for multi-agent systems, including protocols, norms, and platforms. His work has appeared in leading AI venues including AAMAS, IJCAI, and AAAI, was a finalist for best paper at AAMAS 2025, and has been supported by EPSRC and Marie Curie Fellowships. Munindar P. Singh Munindar P. Singh is the SAS Institute Distinguished Professor of Computer Science at North Carolina State University. His research has made major contributions to models of interaction, including formalizations of intentions, social commitments, social semantics for communication, and declarative communication models. He is a Fellow of AAAI, AAAS, ACM, and IEEE, and has received major awards from ACM SIGAI, IFAAMAS, and IEEE. Local Information The Venue The EUMAS 2026 conference will be held at Malmö University, which is located in southern Sweden. Malmö is Sweden’s third biggest city and can be easily reached by train, bus, car, and plane. The conference will take place in Malmö University’s Niagara building. Address for Niagara: Nordenskiöldsgatan 1, 211 19 Malmö . The Conference site can be accessed by the following means of transportation: By plane : If traveling by plane, Copenhagen Airport (Kastrup, EKCH) is a convenient choice with over 200 direct routes. From the airport terminal, you can take the commuter train to Malmö, which will take around 25 minutes: Öresund train to Malmö Central Station. Malmö has an own airport as well (Sturup, ESMS): take the Airport buses to Malmö Central. Copenhagen Kastrup is often the more convenient choice for traveling to Malmö. By train From Malmö Central it is a 5 minutes walk to reach the building Niagara. Malmö can be reached by night train from Berlin/Hamburg (DE) via Copenhagen (DK). By taxi : Uber and Bolt are widely used ride-sharing applications in Malmö. By car : If you prefer to take your car, there are parking garages in the area (32 SEK/h and 165 SEK/day). Accommodation Options Looking for a place to stay? Below you’ll find a curated selection of hotels located just a short distance from the conference venue. Please note that accommodation is not included in the conference registration . Malmö University has arranged special discounted rates at several nearby hotels through block bookings for EUMAS 2026 participants. Rooms are limited and offered on a first-come, first-served basis, so we encourage you to secure your stay early. Nearby Hotels Best Western Plus Hotel Noble House (4 star) In the heart of the city stands Hotel Noble House, a magnificent gem that enriches the city's skyline. With an unbeatable location adjacent to the city's central points, this is your perfect retreat. Here, you will not only find a place to stay but also a meeting place where the extraordinary becomes everyday. Our proximity to culture, shopping, nightlife, and lush parks completes your experience. Wake up to breathtaking views of the sea or the vibrant life of the city from many of our rooms. For detailed information and to book your stay with us, please visit our website. Address: Per Weijersgatan 6, 211 34 Malmö ( Google maps , ca. 750m / 10 min walk from the conference venue) Visit website Story Hotel Studio (4 star) Down the street from Niagara and Orkanen, where the conference is being held, we find the Story hotel, a boutique hotel with modern rooms and a great view of Malmö’s city center or the Öresund Bridge and the sea. On the 14th floor of the hotel there is a bar and a large outdoor terrace with impressive views. Address: Tyfongatan 1, 211 19 Malmö ( Google maps , ca. 500m / 7 min walk from the conference venue) Visit website Clarion Hotel Malmö Live (4 star) Just across the street from Niagara, Clarion Hotel Malmö Live is a new landmark in the city’s skyline. Newly built, fresh and with all the amenities you could wish for, including a bar with great views of the city. Address: Dag Hammarskjölds torg 2, 211 18 Malmö ( Google maps , ca. 100m / 2 min walk from the conference venue) Visit website Comfort Hotel (3 star) Right next to Malmö Central is the Comfort Hotel, a nice mix of a 19th century market hall with dizzying ceiling heights, and a modern interior with a rock feel. Here you can play boules, table tennis and table football in their Playground for grown-ups. Address: Carlsgatan 10C, 211 20 Malmö ( Google maps , ca. 800m / 8 min walk from the conference venue) Visit website Organising Committee Nosheen Abid (Malmö University) Harko Verhagen (Stockholm University) Programme We are delighted to announce the programme for EASSS 2026. This years programme has been organised around 4 key research areas of the Multi-Agent Systems Community: Applications of MAS Reinforcement Learning (RL) Coordination, Organisations, Institutions, Norms and Ethics (COINE) Engineering Multi-Agent Systems (EMAS) Agent-Based Modelling and Simulation (ABMS) Each day will focus on one of these areas and will consist a keynote talk by a leading researcher together with one or two tutorials on that area. Along side this, we will be running a series of working groups where school participants will work together to develop insights into a self selected research topic. At the end of the workshop, each group will present their findings. Following this, they will write a group report which will be published on arxiv.org and linked to from the school website. Finally, we have also added an additional day to the workshop (Saturday 24th August) when we will run a hackathon challenge. Monday Tuesday Wednesday Thursday Friday Saturday 9:00 Registration COINE Keynote Prof. Maite Lopez Sanchez RL Keynote Prof. Stefano V. Albrecht EMAS Keynote Prof. Viviana Mascardi ABMS Keynote Gary Polhill Hackathon 9:30 10:00 Welcome Tutorial 1: Deep RL Tutorial 3: Current Trends in Argumentation Dynamics Tutorial 4: Engineering Safe MAS Tutorial 6: HPC & ABM 10:30 School Keynote: Prof. Munindar Singh 11:00 11:30 B R E A K 12:00 Me-in-3 Introduce yourself Tutorial 1: Deep RL Tutorial 3: Current Trends in Argumentation Dynamics Tutorial 4: Engineering Safe MAS Tutorial 6: HPC & ABM 12:30 13:00 13:30 L U N C H 14:00 14:30 Applications Keynote: Dr Panagiotis Tsarchopoulos Tutorial 2: Continual Learning Group Work Tutorial 5: Game Theoretic Verification Group Work 15:00 15:30 Idea Generation 16:00 B R E A K W R A P U P B R E A K 16:30 Group Work Tutorial 2: Continual Learning Walking Tour of Dublin City Tutorial 5: Game Theoretic Verification Group Work & Presentations Demonstrations & Prize Giving 17:00 17:30 18:00 W R A P U P W R A P U P Social: Welcome Drinks Irish Dancing Irish Pub Visit Dinner (T.B.C.) Keynote Speakers School Keynote: Sociotechnical Systems: History, Principles, and Programming Professor Munindar Singh A sociotechnical system (STS) comprises a social tier of stakeholders (people and organizations) and a technical tier of computational entities and resources. An STS exists to advance the requirements and values of its stakeholders and is governed through norms between them. STSs can be engineered or emergent and are usually both. The STS conception accords with many of our intuitions about the real world and it is obvious that multiagent systems would be a way to realize STSs. Yet it is not clear how to construct an STS. In the first part of the talk, I give a quick historical overview of multiagent systems (and what was called distributed AI) leading up to the modern era. I also describe how STSs relate to challenges and opportunities for research on autonomous agents and multiagent systems. In the second part of the talk, I describe research on STSs terms that avoids the limitations of current approaches, especially with respect to autonomy. I introduce interaction protocols and how to marry flexibility and rigor and describe how we can reason about norms and agent operations jointly. Applications Keynote: Multi-Agent Systems in Smart Cities Dr Panagiotis Tsarchopoulos As urban environments evolve into highly interconnected and complex systems, Multi-Agent Systems (MAS) provide a robust framework for managing various smart city components. This tutorial provides an overview of how MAS can be applied across a wide array of smart city domains, including urban management, transportation, energy, public safety, smart homes and environmental monitoring. The session will delve into the practical aspects of integrating MAS into smart city infrastructure, supported by real-world examples and case studies that demonstrate implementations in various cities. Participants will gain an understanding of how MAS can optimize the functioning of these smart city systems, leading to more efficient, scalable, and resilient urban environments. COINE Keynote: Inducing Ethical Behaviour in Autonomous Agents through Value Alignment Professor Maite Lopez Sanchez In this keynote, we explore how ethical values can shape the behaviour of autonomous agents. We begin with a concise introduction to the mathematical formalization of moral/ethical values, providing the foundation for their practical application in multi-agent systems. Next, we delve into various approaches to value alignment in the context of decision-making and learning processes. Special attention will be given to optimization techniques and reinforcement learning as powerful tools for aligning agent behaviour with ethical standards. Finally, we will demonstrate the application of these concepts through a series of simplified yet illustrative use cases, highlighting the potential of integrating ethics into autonomous decision-making. RL Keynote: From Deep Reinforcement Learning to LLM-based Agents: Perspectives on Current Research Associate Professor Stefano V. Albrecht Since the recent successes of large language models (LLMs), we are beginning to see a shift of attention from deep reinforcement learning to LLM-based agents. While deep RL policies are typically learned from scratch to maximise some defined return objective, LLM-agents use an existing LLM at their core and focus on clever prompt engineering and downstream specialisation of the LLM via supervised and reinforcement learning techniques. In this talk, I will first provide a broad overview of my group's research in deep RL, which focuses among other topics on developing sample-efficient and robust RL algorithms for both single- and multi-agent control tasks, including industry applications in autonomous driving and multi-robot warehouses. I will then present our recent research into LLM-agents, where we propose an approach for household robotics that takes into account user preferences to achieve more robust and effective planning. I will conclude with some personal observations about the state of LLM-agent research: (a) many papers in this field follow essentially the same recipe by focussing on prompt engineering and downstream specialisation; (b) this recipe makes their scientific claims brittle as they depend crucially on the specific LMM engine, and (c) LLMs are not natively designed to maximise objectives for optimal control and decision making. Based on these observations, I believe some fruitful research avenues can be identified. EMAS Keynote: Engineering Multiagent Systems: an introduction Professor Viviana Mascardi As any piece of software, agents and MAS must be modeled, designed, implemented, tested. In this talk, we will discuss the stages required for engineering MAS, along with tools and methods supporting them. ABMS Keynote: Why is agent-based modelling such an awkward customer for institutional HPC? Gary Polhill This talk will briefly introduce agent-based modelling, which is a kind of computer simulation that explicitly represents the emergent dynamics from the interactions of heterogeneous interacting agents. Agents can represent people, but also proteins, plants, non-human animals, as well as households, businesses, and even nation states. After giving some examples of agent-based models from my own work, I will then show various ways in which high-performance computing (HPC) is, if not essential for studying agent-based models, then at least highly advantageous. However, the ways in which HPC access is institutionalized mean agent-based modellers are not typically using these resources, with work still stuck on personal computing devices. New solutions are needed, some of which might even entail some fun computing science. Tutorials Tutorial 1: Deep Reinforcement Learning: Foundations and Practical Environment Setup for Real- World Applications This tutorial delves into the field of reinforcement learning (RL), a specialized area of machine learning focused on developing autonomous agents that behave optimally within specific environments. The tutorial will begin by covering fundamental RL concepts such as agents, environments, and learning paradigms, before discussing why deep learning is increasingly employed to solve complex, high-dimensional decision-making challenges. The session will introduce two principal types of deep RL algorithms: value-based and policy-based methods, each underscored by their respective applications and benefits. Following the theoretical overview, the tutorial will transition into a hands-on component where participants will learn to set up a training environment tailored for RL agents. This part of the tutorial will include a practical introduction to OpenAI’s Gym library and references to prominent libraries that implement deep RL algorithms. We will wrap up by tackling common deep RL challenges, such as managing the balance between exploration and exploitation and overcoming convergence issues. This comprehensive approach will provide attendees with the foundational knowledge necessary to initiate their own RL environments for custom projects. Tutor: Franco Terranova, University of Lorraine Tutorial 2: Continual Learning Continual learning is a fundamental challenge in artificial intelligence, focusing on the ability of agents to learn continuously from a stream of data while retaining previously ac- quired knowledge. This tutorial provides a comprehensive overview of continual learning techniques, ranging from theoretical foundations to practical applications. Participants will gain insights into the latest advancements in this field and learn how to address the issues of catastrophic forgetting and model stability. Through hands-on exercises and case studies, attendees will explore how continual learning can be applied to real-world problems in various domains. Tutor: Andrii Krutsylo, Polish Academy of Sciences Tutorial 3: Current Trends in Argumentation Dynamics Abstract argumentation is a simple model for representing conflicting pieces of information and reasoning from it. In particular, it can be used to model debates (e.g. for deliberation or negotiation) between several agents. In this tutorial, we will review the basic notions of abstract argumentation, and then focus on argumentation dynamics. This topic has received much attention in the last 15 years, with two main types of research questions: 1. given an information about the acceptability of arguments, how can we modify the argumentation framework to comply with this information? 2. given a mod- ification of the argumentation framework, what is the impact of this modification on the acceptability of arguments? The first question is related to strategic aspects (how can an agent convince her opponent to agree with her?), while the second question is mainly about computational aspects (how can we re-compute efficiently the acceptability status of arguments?). We will present the main contributions about both these questions, motivated by applications in the domain of (argument-based) automated negotiation. Tutor: Jean-Guy Mailly, IRIT, University of Toulouse Capitole Tutorial 4: Engineering Safe Multiagent Systems: an Introduction to Formal and Runtime Verifica- tion of Agents and MAS In this tutorial we will discuss the importance of properly engineering agents and MAS, and we will introduce formal verification as a means to engineer safe systems. We will hence in- troduce the notions of formal and semi-formal verification, with special attention to runtime verification, and we will provide an overview on the literature on this topic, to clarify the context and the achieved results. Finally, we will go into the details of runtime verification of MAS, exploiting the RML Runtime Monitoring Language1 as a tool for showing demos and examples. Tutor: Professor Viviana Mascardi, Professor Davide Ancona, Professor Angelo Ferrando Tutorial 5: Game-Theoretic Verification of Multi-Agent Systems Formal verification addresses the issue of correctness, which is a fundamental concern in computer science. In the context of multi-agent systems, rational verification is a game- theoretic counterpart of the conventional formal verification of computing systems. The rational verification problem is concerned with checking which properties will hold in a system when its constituent agents are assumed to behave rationally in pursuit of in- dividual objectives. In this tutorial, we will introduce the fundamental framework for rational verification, including concepts such as models of games, temporal logic, model and equilibrium checking problems, and the Reactive Modules modelling language. We will also present EVE, a formal verification tool that can be used to solve the most impor- tant decision problems in rational verification. We will show how we can model examples of multi-agent systems and use EVE to verify some given properties. Tutor: Professor Muhammad Najib Tutorial 6: High-Performance Computing with Agent-Based Models This course will briefly introduce the steps you need to take to use your agent-based model on high-performance computing facilities. It focuses on agent-based models developed using NetLogo, and potentially other environments based on the Java Virtual Machine, but contains material relevant to any agent-based model in whatever language. It comprises a cut-down version of an earlier two-day tutorial on the same subject Tutor: Gary Polhill --> Colocated Events We are pleased to announce a number of events will take place immediately after EASSS 2026: European Conference on Multi-Agent Systems (EUMAS 2024) Joint Distributed Knowledge Graphs (COST CA 19134) & W3C Web Agents Community Group Workshop A Special Joint-Registration Offer is available for EASSS attendees who also wish to attend EUMAS. --> Local Information Please find information on the venue and accomodation. The Venue UCD is one of Europe's leading research-intensive universities; an environment where undergraduate education, masters and PhD training, research, innovation and community engagement form a dynamic spectrum of activity. UCDs main campus is an extensive parkland estate of 133 hectares in South Dublin. Details of available transport links can be found here . The venue for the summer school is the UCD School of Computer Science . This is labelled as building 18 on the map below. on the map below. Leap Card Leap Cards are a prepaid travel card that is the easiest way to pay your fare on public transport around Ireland. It is valid on most TFI services and commercial bus operators throughout Ireland. It’s more convenient because you don’t have to carry cash or queue at ticket machines and it can save you money because fares are usually up to 30% less than cash single tickets. TFI 90 Minute Fare When you have a leap card, you can travel anywhere in Dublin for 90 minutes for just €2. This includes all Dublin Bus, Go-Ahead Ireland, the Luas (tram) and the DART/Commuter Services (local train). Accommodation Options Much of the local accommodation is available through Booking.com . Occassionally, you can find better deals on their own websites. On Campus: UCD Accommodation UCD has extensive student residences, but it is mostly rented out to groups attending English Language Camps over the summer. What remains is available through Booking.com at a rate of around €145 per day. Book Now Nearby Hotels: Radisson St Helens (5 star) Closest external hotel to UCD. Very popular with limited availability. Prices start around €200 per night, but can rise quicky and steeply. Book Now Talbot Hotel, Stillorgan (4 star) This hotel is one of the closest hotels to UCD. It is around a 20-30 minute walk or around 10 minutes on a bus. Prices range from around €145 per night upwards depending on availability. Book Now Alternatives: Premier Inn Hotel chain with accommodation at various locations. Rooms are €150+ per night. Would require a bus journey to get to UCD - duration depends on location. Book Now AirBnb AirBnb is very popular in Ireland and there are many options. Rooms can be rented for €80-100 per night. For those of you in groups, entire apartments can be rented for similar or better rates. Set "University College Dublin" as the location when you search. Book Now Generator Hostel A popular hostel in the city centre. Shared dormatories are available for around €50 per night. Bus to UCD is around 10-20 minutes walk. The bus takes 30-60 minutes depending on traffic. Book Now Jacobs Inn Hostel Cheaper alternative in the city centre. Around 30-60mins journey to UCD on the Dart or via Bus. Shared dormatories available from around €40 per night. Book Now --> Sponsors & Organisation Organising Committee Fatemeh Golpayegani (University College Dublin) Rem Collier (University College Dublin) Alessandro Ricci (Unversity of Bologna) Sponsors --> Copyright © 2026 EURAMAS · Contact Privacy · Imprint -->