Human Agents and Cooperative Artificial Societies (HACAS)

Human Agents and Cooperative Artificial Societies (HACAS)

Track chairs

The term “human agent” combines concepts such as artificial societies, virtual crowds and synthetic populations. These concepts are used in various fields, such as smart city planning, emergency management and national security. Agent-based simulation models involving human agents can capture the decision-making processes of individuals as they interact with and respond to other individuals and their environment. They are also used for various research tasks, such as policy decision support, what-if scenarios, predictive modeling, and guiding data collection.

Of particular interest are artificial societies in which the behavior of individual agents is guided by findings from computational social sciences and calibrated using data from the real world. These heterogeneous, often cooperative agents participate in social networks, which can be physical (e.g. workplaces, schools, sporting events) or virtual (e.g. chat groups with shared interests). Human agents are generally mobile in an environment where they are exposed to social factors and physical constraints. Since multi-agent systems are based on the distributed AI paradigm, autonomy and learning, e.g. in the form of reinforcement learning, are essential components of the system.

Despite the many applications and resulting publications, fundamental methodological challenges remain in modeling realistic human behavior. These challenges include the representation of agents, cooperative behavior, individual and collective learning, the construction of behavioral rules, the incorporation of behavioral theories and their assumptions, the validation and calibration of models representing complex social phenomena, and the detection and management of emergent behavior at the societal level.

Therefore, authors are encouraged to submit papers related to, but not limited to, the following areas:

  • Design and implementation of human agents and artificial societies (e.g., case studies, analyses of moral and ethical considerations).
  • LLM (Large Language Model)-based agents.
  • Learning / intelligent agents.
  • The role of the non-stationary environment for the simulation result.
  • Applications of human agents and cooperative artificial societies (e.g. modeling of group decisions and collective behavior, emergence of social structures and norms, dynamics of social networks).
  • Data collection for artificial societies (e.g., using simulations to identify data gaps, population simulations with multiple data sources, use of the Internet of Things).
  • Participatory modeling and simulation.
  • Policy development and evaluation through simulations.
  • Improved models of social behavior.
  • Simulations of societies as public educational tools.
  • Mixed-methods (e.g., analyzing or generating text data with artificial societies, combining machine learning and artificial societies).
  • Models of individual decision-making, mobility patterns, or socio-environmental interactions.
  • Testbeds and environments to facilitate artificial society development.
  • Addressing long-standing challenges (model validation, re-use, communication).