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.

This computational model accompanies the article “The Informational Assumptions of Schelling Segregation: An Agent-Based Decomposition of Cue Inference, Cultural Schemas, and Residential Sorting.” It implements an agent-based model in which agents infer latent neighborhood-type classes from noisy non-demographic cues through schema-specific diagnostic mappings, update beliefs, and relocate when satisfaction on a preferred latent class falls below a threshold.

The model serves as a mechanism-isolation device for studying the informational architecture underlying Schelling-style residential sorting. It includes the principal sweep configuration (14,400 runs across a seven-parameter grid), a disagreement-metric sub-sweep with permutation-minimized Jensen-Shannon divergence recorded natively, controls (positive, negative, and frozen-belief), a paired-seed cue-channel perturbation experiment, and selected-cell sensitivity sweeps for cue persistence and home-biased mobility.

The full ODD protocol, parameter manifests, deterministic seed schedules, processed outputs, regenerable figure scripts, the verification test suite, and the satisfaction-mapping audit document are included. Every reported run is deterministic given a (config, seed) pair, and an included audit script verifies bit-for-bit replay on sampled runs.

ARMM is a theoretical agent-based model that formalizes Murra’s Theory of Verticality (Murra, 1972) to explore how multi-zonal resource management systems emerge in mountain landscapes. The model identifies the social, political, and economic mechanisms that enable vertical complementarity across ecological gradients.
Built in NetLogo, ARMM employs an abstract 111×111 grid divided into four Andean ecological zones (Altiplano, Highland, Lowland, Coast), each containing up to 18 resource types distributed according to ecological suitability. To test general theoretical principles rather than replicate specific geography, resource locations are randomized at each model initialization.
Settlement agents pursue one of two economic strategies: diversification (seeking resource variety, maximum 2 units per type) or accumulation (maximising total quantity, maximum 30 units). Agents move between adjacent zones through hierarchical decision-making, first attempting peaceful interactions—coexistence (governed by tolerance) and trading (governed by cooperation)—before resorting to conflict (theft or takeover, governed by belligerence).
The model demonstrates that vertical complementarity can emerge through fundamentally different mechanisms: either through autonomous mobility under political decentralization or through state-coordinated redistribution under centralization. Sensitivity analysis reveals that belligerence and economic strategy explain approximately 25% of outcome variance, confirming that structural inequalities between zones result from political-economic organization rather than environmental constraints alone.
As a preliminary theoretical model, ARMM intentionally maintains simplicity to isolate core mechanisms and generate testable hypotheses. This foundational framework will guide future empirically-calibrated versions that incorporate specific archaeological settlement data and geographic features from the Carangas region (Bolivia-Chile border), enabling direct comparison between theoretical predictions and observed historical patterns.

The FRAMe (Flood Resilience Agent-Based Model) serves as a framework designed to simulate flood resilience dynamics at the community level, focusing on a rural settlement in the Mekong River Basin. Integrating empirical data from extensive surveys, Bayesian networks, and hydrological simulations, the framework quantifies resilience as a trade-off between robustness (resistance to damage) and adaptability (capacity for dynamic response). Agents include households, governments, and other actors, linked by social and governance networks that facilitate knowledge transfer, resource distribution, and risk communication. FRAMe incorporates mechanisms for flood forecasting, policy interventions (education, aid, insurance), and individual and collective decision-making, grounded in Protection Motivation Theory and MoHuB frameworks. The framework’s spatially explicit design leverages GIS data, which supports scenario testing of governance structures and stakeholder interactions. By examining policy scenarios and agent behavior, FRAMe aims to inform adaptive flood management strategies and enhance community resilience.

Negotiation plays a fundamental role in shaping human societies, underpinning conflict resolution, institutional design, and economic coordination. This article introduces E³-MAN, a novel multi-agent model for negotiation that integrates individual utility maximization with fairness and institutional legitimacy. Unlike classical approaches grounded solely in game theory, our model incorporates Bayesian opponent modeling, transfer learning from past negotiation domains, and fallback institutional rules to resolve deadlocks. Agents interact in dynamic environments characterized by strategic heterogeneity and asymmetric information, negotiating over multidimensional issues under time constraints. Through extensive simulation experiments, we compare E³-MAN against the Nash bargaining solution and equal-split baselines using key performance metrics: utilitarian efficiency, Nash social welfare, Jain fairness index, Gini coefficient, and institutional compliance. Results show that E³-MAN achieves near-optimal efficiency while significantly improving distributive equity and agreement stability. A legal application simulating multilateral labor arbitration demonstrates that institutional default rules foster more balanced outcomes and increase negotiation success rates from 58% to 98%. By combining computational intelligence with normative constraints, this work contributes to the growing field of socially aware autonomous agents. It offers a virtual laboratory for exploring how simple institutional interventions can enhance justice, cooperation, and robustness in complex socio-legal systems.

This base model uses an agent-based approach to represent heterogeneous farmers’ trading partners selection among multiple recipients (other farmers, village collectives, and firms). Each period, a potential transfer-out farmer decides whether to transfer based on a net-return versus transaction-cost trade-off; if transferring, the farmer selects the counterparty with the highest expected profit. Meanwhile, social learning—operationalized as logistic accumulation of neighborhood experience—continuously updates uncertainty, which in turn shapes transaction costs and subsequent decisions.

BESTMAP-ABM-DE is an agent-based model to determine the adoption and spatial allocation of selected agri-environmental schemes (AES) by individual farmers in the Mulde River Basin located in Western Saxony, Germany. The selected AES are buffer areas, cover crops, maintaining permanent grassland and conversion of arable land to permanent grassland. While the first three schemes have already been offered in the case study area, the latter scheme is a hypothetical scheme designed to test the impact of potential policy changes. For the first model analyses, only the currently offered schemes are considered. With the model, the effect of different scenarios of policy design on patterns of adoption can be investigated. In particular, the model can be used to study the social-ecological consequences of agricultural policies at different spatial and temporal scales and, in combination with biophysical models, test the ecological implications of different designs of the EU’s Common Agricultural Policy. The model was developed in the BESTMAP project.

The purpose of this model is to analyze how different management strategies affect the wellbeing, sustainability and resilience of an extensive livestock system under scenarios of climate change and landscape configurations. For this purpose, it simulates one cattle farming system, in which agents (cattle) move through the space using resources (grass). Three farmer profiles are considered: 1) a subsistence farmer that emphasizes self-sufficiency and low costs with limited attention to herd management practices, 2) a commercial farmer focused on profit maximization through efficient production methods, and 3) an environmental farmer that prioritizes conservation of natural resources and animal welfare over profit maximization. These three farmer profiles share the same management strategies to adapt to climate and resource conditions, but differ in their goals and decision-making criteria for when, how, and whether to implement those strategies. This model is based on the SequiaBasalto model (Dieguez Cameroni et al. 2012, 2014, Bommel et al. 2014 and Morales et al. 2015), replicated in NetLogo by Soler-Navarro et al. (2023).

One year is 368 days. Seasons change every 92 days. Each step begins with the growth of grass as a function of climate and season. This is followed by updating the live weight of animals according to the grass height of their patch, and grass consumption, which is determined based on the updated live weight. Animals can be supplemented by the farmer in case of severe drought. After consumption, cows grow and reproduce, and a new grass height is calculated. This updated grass height value becomes the starting grass height for the next day. Cows then move to the next area with the highest grass height. After that, cattle prices are updated and cattle sales are held on the first day of fall. In the event of a severe drought, special sales are held. Finally, at the end of the day, the farm balance and the farmer’s effort are calculated.

The model represents urban commuters’ transport mode choices among cars, public transit, and motorcycles—a mode highly prevalent in developing countries. Using an agent-based modeling approach, it simulates transport dynamics and serves as a testbed for evaluating policies aimed at improving mobility.

The model simulates an ecosystem of human agents who decide, at each time step, which mode of transportation to use for commuting to work. Their decision is based on a combination of personal satisfaction with their most recent journey—evaluated across a vector of individual needs—the information they crowdsource from their social network, and their personal uncertainty regarding trying new transport options.

Agents are assigned demographic attributes such as sex, age, and income level, and are distributed across city neighborhoods according to their socioeconomic status. To represent social influence in decision-making, agents are connected via a scale-free social network topology, where connections are more likely among agents within the same socioeconomic group, reflecting the tendency of individuals to form social ties with similar others.

…

The Agent-Based Model for Multiple Team Membership (ABMMTM) simulates design teams searching for viable design solutions, for a large design project that requires multiple design teams that are working simultaneously, under different organizational structures; specifically, the impact of multiple team membership (MTM). The key mechanism under study is how individual agent-level decision-making impacts macro-level project performance, specifically, wage cost. Each agent follows a stochastic learning approach, akin to simulated annealing or reinforcement learning, where they iteratively explore potential design solutions. The agent evaluates new solutions based on a random-walk exploration, accepting improvements while rejecting inferior designs. This iterative process simulates real-world problem-solving dynamics where designers refine solutions based on feedback.

As a proof-of-concept demonstration of assessing the macro-level effects of MTM in organizational design, we developed this agent-based simulation model which was used in a simulation experiment. The scenario is a system design project involving multiple interdependent teams of engineering designers. In this scenario, the required system design is split into three separate but interdependent systems, e.g., the design of a satellite could (trivially) be split into three components: power source, control system, and communication systems; each of three design team is in charge of a design of one of these components. A design team is responsible for ensuring its proposed component’s design meets the design requirement; they are not responsible for the design requirements of the other components. If the design of a given component does not affect the design requirements of the other components, we call this the uncoupled scenario; otherwise, it is a coupled scenario.