Researchers tend to model people as individuals rather than as members of groups. This approach diminishes the impact of altruism and other group-supporting behaviors. For example, walkers may move slower than their capability to retain group cohesion. Current modeling approaches to capture group formation and dynamics lack the strategic elements required to model the complexity of human decision-making. Game theory provides a mechanism to introduce this strategic behavior. This article investigates strategic group formation through the introduction of cooperative game theory techniques into an agent-based model and simulation (ABMS). It shows some empirical results from this introduction. The approach requires looking at the Core instead of the more common Nash Equilibrium. The simulation outputs show some agents forming a large dominant group, much like a real-world mob. The model and results are relevant to policymakers trying to understand how humans navigate an environment through strategic social interactions.

We examine the potential of prompting a large language model-based chatbot, ChatGPT, to generate functional simulation model code from a prose-based narrative. The simple narrative describes how the mode of transportation for elementary school students changed due to the COVID-19 pandemic and related factors, including a lack of available bus drivers, lack of mask enforcement on buses, and inclement weather. We document the process of providing this narrative to ChatGPT and further prompting the chatbot to generate model code to represent the narrative and to make it executable. We test ChatGPT’s ability to use prose descriptions of a phenomenon to generate simulation models using three paradigms: discrete event system, system dynamics, and agent-based modeling. Our findings reveal that ChatGPT could not produce concise or executable models, facing higher difficulty when asked to do so in programming languages it was less familiar with. This analysis underscores the strengths and limitations of the current state of this technology for modeling and simulation. Furthermore, we propose how future advancements in Large Language Models may aid the simulation modeling process, increasing transparency and participation in multidisciplinary team efforts.

Large language models (LLMs) excel in providing natural language responses that sound authoritative, reflect knowledge of the context area, and can present from a range of varied perspectives. Agent-based models and simulations consist of simulated agents that interact within a simulated environment to explore societal, social, and ethical, among other, problems. Simulated agents generate large volumes of data and discerning useful and relevant content is an onerous task. LLMs can help in communicating agents’ perspectives on key life events by providing natural language narratives. However, these narratives should be factual, transparent, and reproducible. Therefore, we present a structured narrative prompt for sending queries to LLMs, we experiment with the narrative generation process using OpenAI’s ChatGPT, and we assess statistically significant differences across 11 Positive and Negative Affect Schedule (PANAS) sentiment levels between the generated narratives and real tweets using chi-squared tests and Fisher’s exact tests. The narrative prompt structure effectively yields narratives with the desired components from ChatGPT. In four out of forty-four categories, ChatGPT generated narratives which have sentiment scores that were not discernibly different, in terms of statistical significance (alpha level $\alpha =0.05$), from the sentiment expressed in real tweets. Three outcomes are provided: (1) a list of benefits and challenges for LLMs in narrative generation; (2) a structured prompt for requesting narratives of an LLM chatbot based on simulated agents’ information; (3) an assessment of statistical significance in the sentiment prevalence of the generated narratives compared to real tweets. This indicates significant promise in the utilization of LLMs for helping to connect a simulated agent’s experiences with real people.

Crowds are a part of everyday public life, from stadiums and arenas to school hallways. Occasionally, pushing within the crowd spontaneously escalates to crushing behavior, resulting in injuries and even death. The rarity and unpredictability of these incidents provides few options to collect data for research on the prediction and prevention of hazardous emergent behaviors in crowds. This study takes a close look at the way states of agitation, such as panic, can spread through crowds. Group composition—mainly family groups composed of members with differing mobility levels—plays an important role in the spread of agitation through the crowd, ultimately affecting the exit density and evacuation clearance time of a simulated venue. This study used an agent-based model of pedestrian movement during the egress of a hypothetical room and adopted an emotional, cognitive, and social framework to explore the transference and dissipation of agitation through a crowd. The preliminary results reveal that average group size in a crowd is a primary contributor to the exit density and evacuation clearance time. The study provides the groundwork on which to build more elaborate models that incorporate sociobehavioral aspects to simulate human movement during panic situations and account for the potential for dangerous behavior to emerge in crowds.

Refugee flight presents a logistics problem for humanitarian aid workers anticipating ebbs and flows of arrivals. These migrations include travel over long distances with little advanced coordination and damaged social networks. The model presented here is based on these two fundamental premises: long distance and strategic en-route coordination. Assuming that over large distances, refugees attempt to construct groups that provide assistance or security as they navigate toward safety, the agent-based model incorporates cooperative game theory to investigate the impact of group formations on egress times. The modeled refugees make decisions based on individual utility functions informed by two factors, speed of the group and group size. Since groups accommodate slower members, they may reform as refugees choose their best available strategies to reach safety. The results indicate a tipping point in average group size as the slowest group members have more of impact in the utility function of the agents.

Festivals in city parks attended by individuals and families are a universal feature of urban life. These venues often have the common attributes of vendors and other obstacles that restrict pedestrian movement through certain areas, as well as fixed number of exits. In this study, the authors build an agent-based model (ABM) that incorporates group cohesion forces into this type of pedestrian egress scenario. The scenario considered was an evacuation of 500 people through a single exit. This allowed an investigation into the use of two different simulated pedestrian's heading updating rules