WORKSHOPS

2nd Workshop on AI for Critical National Infrastructure (AI4CNI-26)

Critical National Infrastructure (CNI) forms the backbone of modern society, yet its increasing complexity requires increasingly autonomous operation and makes it vulnerable to cascading failures and cyber-physical threats. The AI4CNI workshop explores the transformative potential of artificial intelligence and multi-agent systems to enhance the efficiency, resilience, and defense of vital services like energy, transportation, communication networks and healthcare.

Adaptive and Learning Agents (ALA)

Autonomous Robots and Multirobot Systems (ARMS)

Robots are agents, too. Indeed, agents researchers often use robotics problems as motivating examples. Both practical and analytical techniques developed by agents researchers influence, and are influenced by, research in autonomous robots and multi-robot systems. Despite the overlap between the agents and robotics research areas, researchers from these communities only have a few opportunities to meet and interact. The Robotics and Control Area of Interest in the main AAMAS conference (formerly, the “Robotics Track”) is one such opportunity. The goal of this workshop is to build on this opportunity, offering an informal and dedicated forum where agents and robotics researchers can interact, discuss promising research directions and open problems, and foster further collaborations.

7th International Workshop on Agents for Societal Impact

This workshop focuses on the design, analysis, and deployment of intelligent agents that contribute positively to society. As AI agents become increasingly autonomous and embedded in real-world systems, it is critical to ensure that their behavior aligns with human values and societal goals, rather than optimizing narrowly defined technical objectives. The workshop provides a forum to discuss how agent-based technologies can be responsibly applied to real-world societal systems, including (but not limited to): healthcare, education, climate, sustainability, conservation, public infrastructure, labor markets, governance and policy design, etc. The goal is to identify new MAS problems in societies, develop novel MAS solutions to resolve social challenges, and learn from the real-world deployment of MAS.

14th International Workshop on Agents in Traffic and Transportation (ATT 2026)

The ATT 2026 workshop aims to bring together researchers and practitioners to exchange ideas and results on how large-scale traffic and transportation systems can be modeled, simulated, controlled, and managed at both micro and macro levels, using autonomous agents and multiagent systems. The workshop welcomes theoretical, methodological, and applied contributions combining machine learning, optimization, control, simulation, and data-driven AI approaches. In particular, work on deep learning and data-centric approaches to address challenges in traffic and transportation are strongly encouraged.

Citizen-Centric Multi Agent Systems 2026 (C-MAS 2026)

Join us for the C-MAS 2026 workshop, where we explore citizen-centric AI and multiagent systems. In today’s world, large-scale AI systems hold the potential to tackle critical societal challenges, from decarbonising our energy system to facilitating on-demand mobility and improving disaster response. However, we often overlook the active role of citizen end users, treating them merely as data providers and service consumers. Our workshop aims to shift this perspective and explore innovative approaches that treat citizen end users as primary agents with diverse needs and preferences. By doing so, we can develop more trustworthy, fair, and widely accepted sociotechnical solutions to pressing societal challenges.

Causal Learning and Reasoning in Agents and Multi-Agent Systems (CLaRAMAS)

CLaRAMAS aims to foster cross-disciplinary exchange and synergistic collaboration between two complementary communities: the AAMAS community and the Causal Learning and Reasoning (CLR) community.
The overarching goal is to bridge these domains by exploring the following open questions: How CLR techniques can enhance agent-based decision-making? How agent-oriented perspectives can leverage the operational deployment of CLR in real-world applications?

Coordination, Organizations, Institutions, Norms and Ethics for Governance of Multi-Agent Systems (COINE)

This workshop is an evolution of the COIN (Coordination, Organizations, Institutions and Norms in Agent Systems) workshop series that ran at various conferences including AAMAS (18 times), IJCAI (twice), AAAI in 2008 and ECAI in 2006 and 2016, and produced 17 volumes of post-proceedings in Springer’s Lecture Notes in Artificial Intelligence. The 18th volume of COINE post-proceedings is in progress. In 2020, ethics was added to the name and acronym (now COINE), and also the notion of governance of MAS was added to the full workshop title as this is the common objective uniting the various threads of research (coordination, organizations, etc.) undertaken. The workshop in the new format has been held six times (2020–2025).

14th International Workshop on Engineering Multi-Agent Systems (EMAS 2026)

EMAS 2026 builds on the long-standing tradition of the Workshop on Engineering Multi-Agent Systems, advancing the design, implementation, and deployment of autonomous agents and Multi-Agent Systems (MAS) through research on theories, architectures, languages, platforms, and methodologies. To engage with emerging augmented language models and agentic systems and build on decades of established MAS engineering approaches, this 14th edition focuses on Hybrid Agent Architectures and Multi-Agent Systems. We invite contributions covering the diversity of approaches to engineering agents and MAS: submissions may focus on established or emerging approaches, as well as hybrid approaches that integrate the two, exploring, among others, questions such as how elements from different agent architectures can be combined to create more capable agents, and how MAS can be designed to ensure interoperability, coordination, and governance among heterogeneous agents.

8th International Workshop on EXplainable, Trustworthy, & Responsible AI & Multi‑Agent Systems (EXTRAAMAS 2026)

The International Workshop on EXplainable, Trustworthy, and Responsible AI and Multi-Agent Systems (EXTRAAMAS) runs since 2019, and is a well-established workshop and forum. It aims to discuss and disseminate research on explainable artificial intelligence, with a particular focus on intra/inter-agent explainability and cross-disciplinary perspectives. In its 8^th edition, EXTRAAMAS 2026 identifies four particular focus topics with the ultimate goal of strengthening cutting-edge foundational and applied research.

The 8th Games, Agents, and Incentives Workshop (GAIW-26)

The focus on games, agents, and incentives in AI venues (including AAMAS, AAAI, & IJCAI) can be judged from the significant proportion of technical program sessions which deal with “economic paradigms”; “mathematical social sciences”; “auctions and markets”; “non-cooperative games”; “cooperative games”; “social choice”. One goal of the workshop is to provide a forum to present the latest research, including research that can benefit from further discussion and feedback. The workshop’s goal is to bring together researchers in the fields related to algorithmic mechanism design, computational social choice, and fair division while providing a platform for cross-fertilization of ideas between junior and senior researchers in these fields.

The workshop fits the type of research valued by the AI and agents communities.

27th International Workshop on Multi-Agent-Based Simulation

MABS focuses on the confluence of social sciences and multi-agent systems, with a strong application/empirical vein, and it emphasizes, (i) exploratory agent-based simulation as a principled way of undertaking scientific research in the social sciences and (ii) using social theories as an inspiration for new frameworks and developments in multi-agent systems. MABS 2026 continues its tradition of fostering cross-fertilisation and innovation in MAS engineering and complex social and sociotechnical systems modeling. The workshop encourages submissions in areas such as simulation methodology and tools, simulation of social and intelligent behaviour, diverse applications, and simulation analytics.

International Workshop on Autonomous Agents and Multi-Agent Systems for Space Applications

This workshop aims at disseminating and sharing recent advances in the use of agent-based and multi-agent-based models and techniques in the Space domain. Indeed, the use of agent-based and multi-agent systems (MAS) in aerospace and space is gaining traction, as they offer a promising approach for modeling and solving distributed, complex and dynamic problems. Sample applications notably include multiple spacecraft operations and maintenance, onboard-ground coordination, mission simulation, multi-mission operation, autonomous navigation, and collective robotics.

NEurosymbolic eXplainable trUstworthy Systems (NEXUS)

The opacity of current deep learning models is a major barrier to adoption where accountability is essential. NEXUS focuses on neurosymbolic reasoning as a foundational approach to building theory, applications, and tools for well-calibrated and trustworthy autonomy. This paradigm moves beyond a narrow focus on formal logic, concerning itself with the integration of deep and reinforcement learning algorithms with a broad spectrum of structured knowledge.

Workshop on Optimization and Learning in Multi-Agent Systems (OptLearnMAS)

The goal of the workshop is to provide researchers with a venue to discuss models or techniques for tackling a variety of multi-agent optimization problems. We seek contributions in the general area of multi-agent optimization, including distributed optimization, coalition formation, optimization under uncertainty, winner determination algorithms in auctions and procurements, and algorithms to compute Nash and other equilibria in games. Of particular emphasis are contributions at the intersection of optimization and learning. See below for a (non-exhaustive) list of topics.

This workshop invites works from different strands of the multi-agent systems community that pertain to the design of algorithms, models, and techniques to deal with multi-agent optimization and learning problems or problems that can be effectively solved by adopting a multi-agent framework.

Rebellion and Disobedience in Artificial Intelligence (RaD-AI)

Should intelligent autonomous agents always obey human commands or instructions? 
We argue that, in some contexts, they should not.
Most existing research on collaborative robots and agents assumes that a “good” agent is one that complies with the instructions it is given and works in a predictable manner under the consent of the human operator it serves (e.g., it should never deceive its operator). The goal of this workshop is to challenge this assumption and to rethink the desired abilities and responsibilities of collaborative agents. These include, for example, exhibiting behavior that attempts appropriate and harm-preventing non-compliance (e.g., safety constraints in autonomous vehicles or training LLMs to avoid potentially harmful or norm-violating output), among others.

Strategic Engineering Workshop (SE)

Real-world interactions are messy; Game Theory is rigorous. Historically, connecting the two required expensive manual modeling. “Strategic Engineering” seeks to automate this pipeline. We ask: How can LLMs serve as architects, translating everyday scenarios into the formal structures that Game Theory (GT) and Multi-Agent Systems (MAS) require? If we can automate the creation of the “world model”, we can unlock the full power of classical GT/MAS reasoning for any situation. We invite submissions that fuse the generative capabilities of LLMs with the reasoning power of GT/MAS, creating a new class of agents capable of navigating complex, strategic environments.