MASTOC-LLM extends the classic Multi-Agent System Tragedy of the Commons (MASTOC) model by replacing hard-coded behavioral rules with autonomous decision-making powered by large language models (LLMs). Three heterogeneous agents manage herds of cows on a shared grassland commons. Each tick, an agent receives a structured prompt describing current resource levels, its own herd size, peer behavior, and — optionally — a rolling memory of recent rounds and messages from neighboring agents. The LLM returns a stocking decision (add, remove, or hold cows) together with a natural-language rationale and, when communication is enabled, a short message to broadcast to peers.

The model is designed to test whether LLM agents spontaneously develop Ostrom-style common-pool resource governance (mutual monitoring, graduated sanctions, graduated rule revision) or instead fall into identifiable failure modes. Preliminary experiments with Claude Haiku 4.5, GPT-5.4-mini, and DeepSeek R1:32b have revealed four recurring collapse patterns — Cooperative Paralysis, Defection Cascade, Overshoot-Panic, and Hybrid Architecture Failure — whose onset timing is sensitive to memory length, inter-agent communication, and the post-training alignment approach of the underlying model.

MASTOC-LLM is intended as a laboratory for generative agent-based modelling (GABM) methodology: it provides a clean, well-understood commons baseline against which LLM behavioral hypotheses can be systematically tested and compared across models, parameter sweeps, and alignment regimes.

The Inspection Model represents a basic food safety system where inspectors, consumers and stores interact. The purpose of the model is to provide insight into an optimal level of inspectors in a food system by comparing three search strategies.

The Inspection Model represents a basic food safety system where inspectors, consumers and stores interact. The purpose of the model is to provide insight into an optimal level of inspectors in a food system by comparing three search strategies.

The Inspection Model represents a basic food safety system where inspectors, consumers and stores interact. The purpose of the model is to provide insight into an optimal level of inspectors in a food system by comparing three search strategies.

MERCURY aims to represent and explore two descriptive models of the functioning of the Roman trade system that aim to explain the observed strong differences in the wideness of distributions of Roman tableware.

What is stable: the large but coordinated change during a diffusion or the small but constant and uncoordinated changes during a dynamic equilibrium? This agent-based model of a diffusion creates output that reveal insights for system stability.

A more complete description of the model can be found in Appendix I as an ODD protocol. This model is an expansion of the Hemelrijk (1996) that was expanded to include a simple food seeking behavior.

The model combines the two elements of disorganization and motivation to explore their impact on teams. Effects of disorganization on team task performance (problem solving)

The purpose of the model is to explore the influence of actor behaviour, combined with environment and business model design, on the survival rates of Industrial Symbiosis Networks (ISN), and the cash flows of the agents. We define an ISN to be robust, when it is able to run for 10 years, without falling apart due to leaving agents.

The model simulates the implementation of local waste exchange collaborations for compost production, through the ISN implementation stages of awareness, planning, negotiation, implementation, and evaluation.

One central firm plays the role of waste processor in a local composting initiative. This firm negotiates with other firms to become a supplier of their organic residual streams. The waste suppliers in the model can decide to join the initiative, or to have the waste brought to the external waste incinerator. The focal point of the model are the company-level interactions during the implementation or ending of synergies.

…

Studies of colonization processes in past human societies often use a standard population model in which population is represented as a single quantity. Real populations in these processes, however, are structured with internal classes or stages, and classes are sometimes created based on social differentiation. In this present work, information about the colonization of old Providence Island was used to create an agent-based model of the colonization process in a heterogeneous environment for a population with social differentiation. Agents were socially divided into two classes and modeled with dissimilar spatial clustering preferences. The model and simulations assessed the importance of gregarious behavior for colonization processes conducted in heterogeneous environments by socially-differentiated populations. Results suggest that in these conditions, the colonization process starts with an agent cluster in the largest and most suitable area. The spatial distribution of agents maintained a tendency toward randomness as simulation time increased, even when gregariousness values increased. The most conspicuous effects in agent clustering were produced by the initial conditions and behavioral adaptations that increased the agent capacity to access more resources and the likelihood of gregariousness. The approach presented here could be used to analyze past human colonization events or support long-term conceptual design of future human colonization processes with small social formations into unfamiliar and uninhabited environments.