Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Checking
Jul 18, 2026·
,,,,,·
0 min read
Stefano Blando
Emmanuele Guerrazzi
Riccardo Porcedda
Giuseppe Squillace
Max Tschaikowski
Andrea Vandin
Abstract
Integrating Large Language Models (LLMs) into traditional Agent-Based Models (ABMs) allows agents to leverage tool calls, semantic reasoning, and adaptive decision-making. In this paper, we evaluate the feasibility, performance, and emergent behavior of agentic ABMs using Mesa and statistical model checking via MultiVeStA. By conducting systematic statistical specification testing across agentic parameter spaces, we quantify the impact of LLM decision-making on macroeconomic and social simulation dynamics.
Type
Publication
Submitted to AISoLA 2026 (arXiv:2607.17948)
Authors
Stefano Blando
(he/him)
PhD Student in Artificial Intelligence
Stefano Blando is a PhD student in the National PhD Program in Artificial Intelligence at
Scuola Superiore Sant’Anna and the University of Pisa. His research lies at the intersection
of AI, agent-based modeling, and economics. He studies adaptive multi-agent systems,
differentiable agent-based models, LLM-based generative agents, and robust quantitative
methods for financial and socio-economic data.