We welcome the submission of technical papers describing significant and original research on all aspects of the theory and practice of autonomous agents and multiagent systems. If you are new to this community, then we encourage you to consult the proceedings of previous editions of the conference to fully appreciate the scope of AAMAS. At the time of submission, you will be asked to associate your paper with one of the following 11 areas of interest:

    Coordination, Organisations, Institutions, Norms and Ethics
    Engineering Multiagent Systems
    Humans and AI / Human-Agent Interaction
    Innovative Applications, in particular addressing the Sustainable Development Goals
    Knowledge Representation, Reasoning, and Planning
    Learning and Adaptation
    Markets, Auctions, and Non-Cooperative Game Theory
    Modelling and Simulation of Societies
    (Multiagent) Reinforcement Learning
    Robotics
    Social Choice and Cooperative Game Theory
    Coordination, Organisations, Institutions, Norms and Ethics

More information on these areas and the topics covered can be found here:

Coordination, Organisations, Institutions, Norms and Ethics
Area Chairs: Marija Slavkovik / Juan Carlos Nieves
Topics:

    Norms, Normative systems
    Organizations and institutions
    Policy, regulation, sanctions, accountability and legislation
    Trust and reputation
    Ethical values in multi-agent systems, including privacy, safety, security and transparency
    Responsible socio-technical systems
    Methodologies for the development of trustworthy AI
    Trustworthy AI education within the scope of MAS

Description: Research in agent and multiagent systems has a long history of developing techniques that balance agent autonomy, adaptation, and distributed social reasoning with system-level considerations such as organisational and institutional policy enforcement addressing safety, security and fairness considerations.  Human-machine cooperation has an increased relevance with the transformation of our societies into socio-technical systems. We need to ensure transparency, foster trust, and ensure social reasoning conforms to societal norms and expectations. We also need to ensure human-machine cooperation is fostered responsibly, within an adequate accountability system and in alignment with the ethical values of individuals concerned.  We encourage the submission of papers that highlight the design, development, evaluation, simulation, and analysis of novel, innovative, and impactful research on issues related to the above topics.

Engineering Multiagent Systems
Area Chairs: Matteo Baldoni / Amit Chopra
Topics:

    Requirements and formal specification
    Architecture and modelling
    Formal verification and validation
    Programming models and languages
    Testing, maintenance, and evolution
    Concurrency, fault tolerance, robustness, performance and scalability
    Sociotechnical systems, norms, and governance
    Responsibility and accountability
    Interoperability, business agreements, and interaction protocols
    BDI-based agents
    Engineering ethical agents
    Tools and testbeds
    Technological paradigms, including microservices, the Web, the IoT, Cloud computing, distributed Ledgers, and Robotics
    Middleware and platforms for MAS
    Engineering learning agents
    Usability
    Applications, including Finance, Health, Agriculture, Autonomous Vehicles and Smart-*

Description: This area invites contributions that focus on general-purpose software abstractions and methodologies (including software systems) that advance the engineering of agents and multiagent systems. Contributions that demonstrate the benefit of such abstractions and methodologies for interesting application domains and other technological paradigms are also welcome. Naturally, the scope of this area spans the entire software engineering lifecycle — from requirements and verification to testing, validation, and evolution.

Humans and AI / Human-Agent Interaction
Area Chairs: Rui Prada / Kary Främling
Topics: 

    Human-agent interaction
    Agent-based analysis of human interactions
    Socially interactive agents
    Trust and explainability in human-agent interactions
    Mixed-initiative and shared autonomy in human-agent interactions
    Groups of humans and agents
    Agents models and architectures for interaction with humans
    Designing for human-agent interaction
    Virtual humans

Description: In a world where AI is increasingly prevalent and hybrid systems with humans and agents interacting becomes more frequent, it is crucial to study and create agents that can understand human social dynamics and have competent interaction with people. Significant challenges arise when transitioning from pure multiagent systems to hybrid systems that need to incorporate mixed-initiative from humans and agents, and sustain different competitive or collaborative social situations. Agents need new models and architectures to better address the interaction with people including, perception and recognition of human activities at different levels, interaction techniques that coordinate well with humans, and concerns for user experience and ethics, such as, trust and explainability. The design of human-agent interaction systems need special concerns that combine requirements from the perspectives of both the agents the humans.The creation of agents with such capabilities can be inspired by human-human interactions and can, additionally, be applied to simulations with virtual humans or support the analysis of data from human social interactions.

Innovative Applications
Area Chairs: Nardine Osman / Vicent Botti
Topics: 

    Innovative applications of agent-based systems tackling SDGs and LNOB
    Innovative applications of agent-based systems tackling issues in ethical AI
    Realistic agent-based models of human organisations
    Evaluation of the cognitive capabilities of agent-based systems
    Integrated applications of agent-based and other technologies
    Challenges and best practices of deploying agent-based technologies to real-world scenarios

Description: The innovative applications area aims to showcase successful applications and novel uses of agent-based technologies. We encourage research on emerging areas of agent-based applications with measurable benefits, focusing on topics such as social good, sustainability, and ethical AI. We invite research that addresses any of the United Nations Sustainable Development Goals (SDGs) (https://sdgs.un.org/goals) or the Leave No One Behind Principle (LNOB) (https://unsdg.un.org/2030-agenda/universal-values/leave-no-one-behind). Given the extensive debate on ethical AI, we also strongly invite research addressing principles such as (but not limited to) beneficence, promotion of human well-being and flourishing, and ensuring AI’s alignment with human values. The innovative applications area is keen to attract research that is not only triggered by real-world applications, but provides realistic beneficial solutions for these applications. Collaborations with relevant stakeholders is highly valued, as it helps demonstrate the feasibility and impact of the work.

Knowledge Representation, Reasoning, and Planning
Area Chairs: Val Goranko / Wojtek Jamroga
Topics: 

    Agent theories and models
    Coalition formation (non-strategic)
    Communication and argumentation
    Distributed problem solving / constraint reasoning
    Formal methods for cybersecurity
    Logics for agent reasoning
    Ontologies for agents
    Single-agent and multi-agent planning and scheduling
    Reasoning about action, plans and change in multi-agent systems
    Reasoning about knowledge, beliefs, and norms in multi-agent systems
    Reasoning about goals and strategies in multi-agent systems
    Reasoning and problem solving in agent-based systems
    Teamwork, team formation, teamwork analysis
    Verification of multi-agent systems

Description: This area includes theoretical or experimental contributions to knowledge representation, reasoning and planning in single-agent and multi-agent systems. Knowledge representation is to be understood broadly, ranging from theoretical contributions (e.g., epistemic, strategic, description, and other logics) to ontologies and beyond. Relevant  forms of reasoning include, for instance, automated reasoning and theorem proving approaches, as well as verification-based approaches, as long as they are applied to, or motivated by reasoning about agents and/or multi-agent systems. Likewise, all approaches to single- and multi-agent search and planning – from motion planning to symbolic planning – and their interplay with other agent components are relevant. 

Learning and Adaptation
Area Chairs: Nils Jansen / Paulo Novais
Topics: 

    (Adversarial) multi-agent systems
    Markov decision processes
    Reasoning and learning under uncertainty
    Co-evolutionary algorithms
    Machine learning and deep learning
    Evolutionary algorithms
    Learning agent capabilities
    Learning agent-to-agent interactions
    Tools & applications

Description: Autonomous Agents must sense, deliberate, decide, and act in potentially complex and uncertain environments. In addition, in many cases, they must interact with other agents and/or humans. Anticipating each situation and hardcoding the appropriate agent behavior becomes impossible as the complexity of the environment and interactions increase. As such, adaptivity and learning are key properties that imbue autonomy to agents operating in the real world. Papers in this area focus on all aspects of single agent and multiagent planning and learning.

Markets, Auctions, and Non-Cooperative Game Theory
Area Chairs: Paolo Turrini / Nicolas Troquard
Topics:

    Auctions and Mechanism Design
    Bargaining and Negotiation
    Behavioural Game Theory
    Evolutionary Game Theory
    Non-Cooperative Games: Equilibrium Concepts
    Non-Cooperative Games: Computational Issues
    Non-Cooperative Games: Theory and Applications
    Practical Applications of Non-Cooperative Game Theory

Description: This area encompasses research on non-cooperative games, specifically focusing on computational aspects such as algorithmic and complexity analysis for equilibrium computation and verification. The track also welcomes theoretical explorations and analysis related to non-cooperative games. In particular, it highlights the ramifications of non-cooperative game theory in various domains such as market and mechanism design, including auctions, bargaining, negotiation, behavioural and evolutionary game theory. Submissions showcasing practical applications of game theory are also strongly encouraged.

Modelling and Simulation of (Artificial) Societies
Area Chairs: Michael Lees / Harko Verhagen
Topics: 

    Analysis of agent-based simulations
    Calibration methods for socio-demographic data
    Agent-based models & Social Networks
    Applications of agent-based simulations in social phenomena (polarisation, inequality,etc.)
    Emergent behaviour
    Engineering agent-based simulations 
    Interactive simulation
    Modelling for agent-based simulation
    Simulation of complex systems
    Simulation techniques, tools and platforms
    Social simulation
    Validation of social simulation systems

Description: Artificial societies are computer simulations or models that are created to emulate and research the behaviour of intricate social systems. These societies simulate the interactions and dynamics of people, animals or other organisms to understand how individual behaviours lead to emergent structures and interactions. Agent-based models of artificial society provide a way to analyse the impact of regulations, incentives and other interventions that help to understand the complex dynamics of society as a whole.

The area aims to find efficient solutions to model and simulate complex societal systems using agents-based models. Important application areas include ecology, biology, economics, transportation, management, organisational, and social sciences in general. In these areas, agent theories, metaphors, models, analysis, experimental designs, empirical studies, and methodological principles, all converge into simulation as a way of achieving explanations and predictions, exploration and testing of hypotheses, and better system designs.

Social Choice and Cooperative Game Theory
Area Chairs: Ulle Endriss / Piotr Skowron
Topics: 

    Voting and Preference Aggregation
    Social Choice and Social Networks
    Judgment Aggregation
    Fair Allocation
    Matching
    Digital Democracy
    Coalition Formation
    Cooperative Games 

Description: This area covers all aspects of social choice theory, the study of the design and analysis of methods for collective decision making, including in particular voting and the fair allocation of resources. It also covers the theoretical, algorithmic, and practical aspects of coalition formation and cooperative game theory.

(Multi-agent) Reinforcement Learning
Area Chairs: Matthijs Spaan / Matt Taylor / Shuyue Hu
Topics: 

    Single- and Multi-agent Reinforcement Learning (RL)
    Markov Decision Processes
    Sequential Decision Making
    RL in partially observable settings
    RL in adversarial settings
    Model-based RL
    Multi-armed Bandits
    Imitation Learning, Inverse RL, and Learning from Demonstration
    Transfer Learning, Lifelong Learning, and Continual Learning in RL settings
    RL Theory
    RL for Robotics
    Human Interaction with RL Agents
    Safe, Robust, Explainable RL
    Neural Architectures for RL
    Applications of RL

Description: For 2024, reinforcement learning will be a separate area from Learning and Adaptation. We welcome all work related to sequential decision making in reinforcement-learning settings. Theoretical, algorithmic, and practical aspects of reinforcement learning are all welcome, and a focus on how reinforcement learning agents interact with other agents or people are particularly welcome.

Robotics
Area Chairs: Luca Iocchi / Joana Campos
Topics: 

    Execution monitoring and Failure recovery for robots
    Explainability, trust and ethics for robots
    Human-robot interaction and collaboration
    Knowledge representation and reasoning in robotic systems
    Long-term (or lifelong) autonomy for robotic systems
    Machine learning for robotics
    Mapping, localisation and exploration
    Mixed Human-Robot teams
    Multi-robot coordination and collaboration 
    Networked systems and distributed robotics
    Robot control
    Robots in adversarial settings
    Social robotics and social interactions
    Swarm and collective behaviour

Description: Robotics is one of the exciting fields in agent research. Both practical and analytical techniques in agent research influence, and are being influenced by, research in autonomous robots and multi-robot systems. We invite papers that advance theory and application of single and multiple robots, with particular emphasis on solutions based on realistic assumptions typically encountered in robotic applications. Papers on integrative research about the interaction between robots and agents (broadly defined) are particularly welcome, but all papers at the intersection of robotics and artificial intelligence (and agent research, specifically) are in the scope of the robotics area at AAMAS.

The reviewing process for each of these areas will be coordinated by dedicated area chairs familiar with the particularities of the area they are responsible for. We reserve the right to transfer a paper to a different area in case we believe that doing so will improve the quality of the reviewing process. You will have the opportunity to react to preliminary versions of the reviews of your paper (so-called “rebuttal”) before we take a final decision regarding the acceptance of your paper.