The 22nd European Conference on Multi-Agent Systems (EUMAS 2025) will be organized on September 3-5, 2025
by
the National University of Science and Technology POLITEHNICA Bucharest 
, Romania, with the support of the Romanian Association for Artificial Intelligence .
EUMAS 2025 is an EURAMAS designated event which follows the tradition of previous editions, and aims to encourage and support activity in the research and development of multi-agent systems, in academic and industrial effort.
The conference aspires to be the primary European forum for researchers interested in the theory and practice of autonomous agents and multi-agent systems. EUMAS enables researchers to meet, present challenges, preliminary and mature research results in an open environment.
EUMAS 2025 features formal proceedings published as part of the Lecture Notes in Computer Science (LNCS) series of Springer.
All dates are AoE, UTC-12
Paper Submission Deadline:
16 May 2025
10 June 2025 (Abstract)
15 June 2025 (Full paper)
Author Notification:
30 June 2025
15 July 2025
Camera Ready Papers:
18 July 2025
15 August 2025 (camera-ready PDF)
30 September 2025 (post-proceedings camera-ready)
EUMAS Conference:
3-5 September 2025
EUMAS 2025 welcomes original, unpublished papers including improved versions of extended abstracts or rejected papers from AAMAS, AAAI and IJCAI 2025. The submission should describe work that has not been previously published, accepted for publication, nor is currently under review by another conference or journal.
All submissions will be peer-reviewed in a single blind fashion. Submission length depends upon the track that you submit to. Additional pages may be used for references and, if needed, a clearly marked appendix. It should be formatted according to Springer’s LNCS format. For templates and instructions for authors, see Conference proceedings guidelines. Authors must submit their papers through the OpenReview submission site as a single PDF file.
This year, EUMAS is accepting submissions across the following tracks:
Topics of interest include, but are not limited to: Action and Planning, Adaptation and Learning; Agent Architectures; Agent Programming Languages; Agent Development Methodologies and Tools; Agent-Based Simulations and Modeling; Agent Organizations and Institutions; Agent-oriented Software Engineering; Agents and Complex Systems; Applications of Multi-agent Systems; Argumentation; Automated negotiation; Biologically inspired approaches; Cognitive Models; Collective and Swarm Intelligence; Collective Intentionality; Communication, Cooperation, and Coordination; Computational Social Choice; Deep Reinforcement Learning in Multi-Agent Domains; Economic Models; Electronic Commerce; Ethical behavior of multi-agent systems; Formal Modelling; Game-Theoretic Methods; Human-Agent Interaction; Logics for Multi-Agent Systems; Logics for Strategic Reasoning; Machine Learning for Multi-Agent Systems; Multi-Agent Learning; LLM powered AI Agents; Multi-agent architectures for XAI; Explainable planning; Explainable negotiation protocols and strategies; Explainable user/agent profiling; Multi-Robot Systems; Negotiation; Self-organization; Semantic Web Agents; Social Networks; Socio-technical Systems; Theories of Agency; Trust and Reputation; Verification; Virtual Agents; Voting and Judgment Aggregation Models for Multi-Agent Systems
This track aims to provide a forum for researchers that are involved in developing agent/MAS toolkits and platforms, or that are using them for the development of applications, to exchange ideas, make proposals, suggest challenges, reports interesting use cases and so on - any aspect that could be of interest in the engineering and using Agent Toolkits.
This track aims to provide opportunities for participants from academia and industry to present their latest developments in agent-based systems. Demonstrations of interest include both applications of multi-agent systems and tools that support developers in the specification, design, implementation and testing of agent systems.
Speaker: Andrei Rusu
Speaker bio: Applied Scientist at UiPath with a PhD in AI, specializing in agent evaluation, benchmarking, and performance optimization. Passionate about developing innovative AI solutions across diverse data types, with hands-on experience in LLM agent design, graph neural networks, and reinforcement learning. Currently focused on advancing agentic automations and harnessing evaluation data to improve agent reliability.
Abstract: TBA.
Speaker: Amit K. Chopra
Speaker bio: Amit K. Chopra is a Senior Lecturer at Lancaster University in the UK. He is interested in interactive, multiagent software abstractions that enable engineering sociotechnical systems, that is, systems involving real-world autonomous principals. Amit's work has been published in conferences such as AAMAS, IJCAI, and AAAI and is currently being applied in the finance domain. He has given several tutorials and invited talks. In a past life, his research was funded by the UKRI and the EU. Amit has a PhD in Computer Science from North Carolina State University.
Abstract: The Agentic AI paradigm is concerned with creating LLM-powered agents that take actions in the real world on behalf of their users. The promise of LLMs lies in their potential to reduce the knowledge engineering effort needed to build agents. Instead of being explicitly programmed, the agents would exploit LLMs to engage in a natural language dialog with their users, figure out the relevant constraints, and act accordingly. Several software frameworks (including protocols) lay claim to realizing Agentic AI. However, these frameworks miss crucial features about the context of real-world actions and their meanings. In a nutshell, they don't get 'multiagent.'
In this talk, I will discuss how Interaction-Oriented Programming (IOP), a ''traditional' multiagent systems engineering approach, can address the shortcomings of current Agentic thinking. IOP's strength lies in declarative modeling abstractions based on norms and interaction protocols. IOP's strength arises from the fact that it addresses three competing aspects of decision making that stem naturally from autonomy: (1) flexibility, (2) correctness, and (3) decentralization. Via free-form interactions, you could say LLMs support flexibility; however, correctness and decentralization remain challenges for Agentic. IOP boasts formal languages, verification tools, and programming models that can be readily exploited to build the bridge to Agentic.
Go directly to: EMAS 1 ABS EMAS 2 Human-Agent Interaction Formal approaches Networks and Learning Demos Short papers
Wednesday, 03 September, 11:30
Paper 24
Towards a Distinct Programming Style for AgentSpeak(L)
Rem W. Collier, Katharine Beaumont, Andrei Ciortea
Paper 39
AgentSpeak(AI): Deliberate Learning Strategies for Plan Acquisition in BDI Agents
Katharine Beaumont, Rem W. Collier
Paper 45
Extending CArtAgO to support the engineering of complex distributed environments at the Knowledge Level
Alessandro Ricci, Andrei Ciortea, Samuele Burattini
Paper 55
Planning with Non-Deterministic Actions and Partially Observable Environments in Jason
Joshua Blondin, Babak Esfandiari
Paper 26
astra-langchain4j: Experiences Combining LLMs and Agent Programming
Rem W. Collier, Katharine Beaumont, Andrei Ciortea
Paper 31
Agent Toolkits: Towards Explainable Agency in ASTRA
Katharine Beaumont, Elena Yan, Samuele Burattini, Rem W. Collier
Paper 33
Integrating JaCa-Unity in VEsNA for Behavioural Realistic VR Simulations
Daniela Briola, Giuseppe Vizzari, Giuseppe Mirra, Andrea Gatti, Matteo Martini, Viviana Mascardi
Thursday, 04 September, 14:30
Paper 16
Stability in Newcomers' Housing: A Story about Anonymous Preferences and Beyond
Grzegorz Lisowski, Šimon Schierreich
Paper 21
A hybrid theoretical and data-driven approach to crowd dynamics modelling
Alessandro Del Vecchio, Alessandro Della Pia, Caio Cesar Graciani Rodrigues
Paper 41
Designing Resilient Markets: Agent-Based Insights into Flash Crashes
Sriram Bharadwaj Rangarajan, Carmine Ventre
Paper 42
Engineering Resilience: An Energy-Based Approach to Sustainable Behavioural Interventions
Arpitha Srivathsa Malavalli, Karthik Sama, Janvi Chhabra, Pooja Bassin, Srinath Srinivasa
Paper 51
Realistic Agent Behaviour based on Concurrent Process Architectures -- Modelling Human Navigation
Sabine Timpf, Franziska Klügl
Thursday, 04 September, 11:30
Paper 2
Mechanism Design With Predictions for Obnoxious Facility Location
Gabriel Istrate, Cosmin Bonchis
Paper 6
Query-Based Committee Selection
Nimrod Talmon, Shiri Alouf-Heffetz, Itay Asher Zimet
Paper 19
Agency and Generation: Friends or Enemies?
Daniela Briola, Rem W. Collier, Angelo Ferrando, Viviana Mascardi
Paper 35
Supporting Accountability in Business Processes
Matteo Baldoni, Cristina Baroglio, Elisa Marengo, Roberto Micalizio
Paper 40
The Agent Metamodel in CATALINA (Cognitive AgenT prActicaL reasonINg Architecture)
Massimo Cossentino, Giovanni Pilato, Guido Averna, Myrto Mylopoulos, John Mylopoulos
Paper 47
Evaluating BDI Agents in ROS: From Basic Integration to Fault-Tolerant Multi-Robot Systems
Qinhan Du, Rafael C. Cardoso
Paper 15
An Intuitionistic Version of Computation Tree Logic
Andrea Capone, Laura Bozzelli, davide catta, Vadim Malvone, Aniello Murano
Thursday, 04 September, 10:00
Paper 1
Stop replacing salt with sugar!'': Towards Intuitive Human-Agent Teaching
Nikolaos Kondylidis, Andrea Rafanelli, Ilaria Tiddi, Annette Ten Teije, Frank Van Harmelen
Paper 13
S4H: A Tool for Synthesizing Human-Like Strategies
Marco Aruta, Vadim Malvone, Aniello Murano
Paper 23
Ethical Decision-Making for Trustworthy Autonomous Systems under Uncertainty
Alison Bifolco, Louise A. Dennis, Giuseppe Primiero
Friday, 05 September, 09:00
Paper 11
Equilibrium Synthesis for Generalised Dining Philosophers Games
Johan Pieter van Rooyen, Nils Timm
Paper 22
Synthesis of Collectively Optimal Strategies for Infinite Runs of Multi-Agent Systems via Maximum Satisfiability Solving
Nils Timm, Steven Jordaan
Paper 29
Allocating resources among non-cooperative agents with Leontief utilities
Ioannis Caragiannis, Nicos Protopapas
Paper 54
Explaining Why Fair Roommate Matchings Do Not Exist
Wassila Ouerdane, Francesco Sabatino, Anaëlle Wilczynski
Paper 60
BOID for smart scheduling: Integrating default logic and generative models for interpretable personalization
Stipe Pandžić, Fabio Dijkshoorn, Jan M. Broersen
Friday, 05 September, 11:30
Paper 12
Successful Misunderstandings: Learning to Coordinate Without Being Understood
Nikolaos Kondylidis, Anil Yaman, Frank Van Harmelen, Erman Acar, Annette Ten Teije
Paper 14
Adaptive Influence Maximization on Hypergraph Topologies
Vincenzo Auletta, Francesco Cauteruccio, Diodato Ferraioli, Grazia Ferrara
Paper 17
Adaptive Multi-Agent System for Dynamic Preference Learning: Application to Mobility
Alexandre Perles, Valérie Camps, Elsy Kaddoum
Paper 27
Controlling the Spread of Two Secrets in Diverse Social Networks
Václav Blažej, Dušan Knop, Šimon Schierreich
Paper 28
Scalable Submodular Policy Optimization via Pruned Submodularity Graph
Aditi Anand, Suman Banerjee, Dildar Ali
Paper 37
Harnessing Stubborn AUVs for Decentralized Decision Strategies in Communication-Limited Environments
Wiebke Frenkel
Wednesday, 03 September, 15:30
Paper 64
Embedding Autonomous Agents in Resource-Constrained Robotic Platforms
Negar Halakou, Juan F. Gutiérrez, Ye Sun, Han Jiang, Xueming Wu, Andres Gomez
Paper 57
FLASH-MAS: towards a state-of-the-art, modular agent deployment environment
Andrei Olaru
Paper 32
AmI HMAS: goal-driven interaction in Smart Environments
Alexandru Sorici, Victor-Vasile Udristoiu, Adina Magda Florea
Wednesday, 03 September, 14:30
Paper 10
Strategic Infrastructure Design via Multi-Agent Congestion Games with Joint Placement and Pricing
Niloofar Aminikalibar, Farzaneh Farhadi, Maria Chli
Paper 20
AI-driven Adaptive Learning for Higher Education
Yao Yao, Horacio Gonzalez-Velez
Paper 25
A 3D Multi-Agent Simulation Architecture for Passenger Flow Optimisation in Mobility Hubs
Edgar Baake, Christian Hyttrek, Patrick Pfau, Aliyu Tanko Ali, Tobias Groth, Mohammad Khodaygani, Stefan Fischer
Paper 38
A Strategyproof Mechanism for Many-to-one One-sided Matching with Bans
Emma Hovorková, Tomáš Valla
Paper 46
Designing Value-Aligned Traffic Agents through Conflict Sensitivity
Astrid Rakow, Maike Schwammberger, Marija Slavkovik, Gleifer Vaz Alves, Joe Collenette
Paper 61
A Computational Approach to Sustainable Policies Evaluation of the Italian Wheat Production System
Gianfranco Giulioni, Edmondo Di Giuseppe, Arianna Di Paola
Paper 53
Exploring Modularity of Agentic Systems for Drug Discovery
Laura van Weesep, Jens Sjölund, Ola Engkvist, Samuel Genheden
Paper 4
Multi-price lottery: A new pricing for ticket lottery sales
Maiko Hara, Yoshifumi Manabe
Paper 62
Modelling Norm Change Through Trendsetters
Beyza Nur Şenol, Seher Ova, Feyza Merve Hafızoğlu
EUMAS 2025 features formal post-proceedings published as part of the Lecture Notes in Computer Science (LNCS) series of Springer. Previous EUMAS proceedings are found here.
The best paper will be invited for fast-track publication of an extended version in the Autonomous Agents and Multi-Agent Systems Journal (JAAMAS).
Details of the registration fee can be found in the table below.
| Until | Student (Fee) | Non-Student (Fee) | |
|---|---|---|---|
|
|
|
|
|
| Normal | 29th of August, 2025 | €220 | €250 |
To register for the conference, please fill out this registration form.
In the form, you will have to select one of the two payment options listed below. Registration will be considered complete upon confirmation of the payment.
Please note that at least one author of each accepted paper must register for the conference, in order for the paper to be included in the post-proceedings.
We are pleased to announce that student authors of accepted papers benefit from a discounted rate for joint registration to the European Agent Systems Summer School (EASSS 2025) and EUMAS.
For more information, please see the EASSS 2025 website.
There are two options for registration payment:
Please include the following information in the transfer description: EUMAS 2025 student / full registration for paper ID, where ID corresponds to the paper ID of the accepted submission you co-authored and which you used in the registration form. Use the value 0 for the paper ID if you are registering without having made a submission.
After the transfer, please send an email to eumas2025@upb.ro with the subject "EUMAS 2025 Registration for paper ID", including a copy of the transfer receipt as proof of payment. If you are registering as a student, please also include a proof of student status (e.g., a copy of your student ID).
Notes:
If you require a letter for a visa, please contact the Organization Committee via email at: eumas2025@upb.ro.
Any additional queries can also be directed to this email address.
The EUMAS 2025 conference is scheduled to be held in Bucharest, Romania’s largest city and the capital. Known for its wide, tree-lined boulevards, glorious Belle Epoque buildings, and a reputation for the high life (which in the 1900s earned its nickname of “Little Paris”), Bucharest is today a bustling metropolis.
The venue of EUMAS 2025 is the National University of Science and Technology POLITEHNICA of Bucharest, 313 Splaiul Independentei, Bucharest, Romania.
The Conference site can be accessed by the following means of transportation:
Much of the local accommodation is available through Booking.com. Occasionally, you can find better deals on their own websites.
There are many apartments available for rent in the vicinity of the conference venue.
You can find them on Airbnb or
Booking.com.
Prices range from 55 to 120 EUR per night, depending on the number of guests and the amenities provided.
To be announced.
Alessandro Ricci, University of Bologna
Alexandru Sorici, University POLITEHNICA of Bucharest
Amit Chopra, University of Lancaster
Andrea Omicini, Università di Bologna
Andrei Ciortea, University St Gallen
Angelo Ferrando, University of Modena and Reggio Emilia
Ann Nowé, Vrije Universitet Brussel
Carles Sierra, IIIA-CSIC
Conor Muldoon, Manchester Metropolitan University
Costin Bădică, University of Craiova
Cristina Baroglio, Università di Torino
Davide Grossi, University of Groningen
Elizabeth Sklar, University of Lincoln
Fabian Lorig, Malmö University
Feyza Merve Hafızoğlu, Istanbul Ticaret University
Florin Leon, Gheorghe Asachi University of Iași
Francesco Belardinelli, Imperial College London
Franco Zambonelli, University of Modena and Reggio Emilia
Franziska Klügl, Örebro University
Frederico Bergenti, Universita di Parma
Gauthier Picard, Onera, Toulouse
Georgios Papasotiropoulos, University of Warsaw
Harko Verhagen, Stockholm University
Ivana Dusparic, Trinity College Dublin
Julian Padget, University of Bath
Katharine Beaumont, University College Dublin
Lars Braubach, Hochschule Bremen
Luis Antunes, Universidade de Lisboa
Marcin Paprzycki, Polish Academy of Sciences
Maria Ganzha, Warsaw University of Technology
Matteo Baldoni, Università di Torino
Mirjana Ivanovic, University of Novi Sad
Natasha Alechina, Utrecht University
Neil Yorke-Smith, TU Delft
Nick Bassiliades, Aristotle University of Thessaloniki
Nicolas Verstaevel, University of Toulouse
Nicoletta Fornara, Università della Svizzera Italiana
Nikolaos Spanoudakis, Technical University of Crete
Olivier Boissier, Ecole des Mines de Saint-Étienne
Paul Davidsson, Malmö University
Piotr Faliszewski, AGH University of Science and Technology
Rafael Cardoso, University of Aberdeen
Rem Collier, University College Dublin
Robert Bredereck, TU Clausthal
Rosaldo Rossetti , University of Porto
Roxana Radulescu, Utrecht University
Sandip Sen, University of Tulsa
Sascha Ossowski, Universidad Rey Juan Carlos
Simon Mayer, University St Gallen
Stefania Monica, University of Modena and Reggio Emilia
Timotheus Kampik, Umea University
Vanina Martinez, IIA-CSIC, Barcelona
Viviana Mascardi, University of Genoa
Yves Lesperance, York University
Zahia Guessoum, Université de Reims Champagne-Ardenne
EUMAS 2025 will partially overlap the European Agents Summer School (EASSS 2025), taking place on September 1-3, 2025, also at POLITEHNICA Bucharest.
Download CFP
