Our mission is to help computational modelers develop, document, and share their computational models in accordance with community standards and good open science and software engineering practices. Model authors can publish their model source code in the Computational Model Library with narrative documentation as well as metadata that supports open science and emerging norms that facilitate software citation, computational reproducibility / frictionless reuse, and interoperability. Model authors can also request private peer review of their computational models. Models that pass peer review receive a DOI once published.
All users of models published in the library must cite model authors when they use and benefit from their code.
Please check out our model publishing tutorial and feel free to contact us if you have any questions or concerns about publishing your model(s) in the Computational Model Library.
Displaying 2 of 2 results Large Language Model clear search
A Benchmark Test for LLM Persona Agents in a Macroeconomic Simulation
Taewan You | Published Thursday, October 08, 2026This model couples a two-asset heterogeneous-agent New Keynesian macroeconomy with a household layer that can be driven in two ways. One is a conventional calibration. The other is a set of large-language-model persona agents built from real survey households in Korea (NaSTaB), the United States (PSID) and Italy (SHIW). Each persona is given its balance sheet, income and prices, and reports consumption, saving and labour supply. A feasibility layer enforces the budget constraint. A conditional-mean surrogate then turns these decisions into a propensity surface. That surface reaches the macroeconomic block through a single channel, the intertemporal marginal propensity to consume matrix. Because of this, a calibrated “twin” can be aligned with the generative layer exactly, and the two can be compared policy by policy.
Both layers are then scored against the held-out consumption of the same households. The model’s role is to serve as a benchmark: it tests whether generative agents add information beyond the balance sheet, and whether that information matches real behaviour.
The deposit contains:
…
MASTOC-LLM (Multi-Agent System Tragedy of the Commons - Large Language Models)
Thomas Tuoti | Published Monday, May 18, 2026 | Last modified Tuesday, May 19, 2026MASTOC-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.