# Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Checking

arXiv: https://arxiv.org/abs/2607.17948 · HTML: https://mlsanity.com/paper/2607.17948/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 55 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 10 of 10)

- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [Automated and Distributed Statistical Analysis of Economic Agent-Based Models](https://mlsanity.com/paper/2102.05405/) (2021)
- [White-box validation of quantitative product lines by statistical model checking and process mining](https://mlsanity.com/paper/2401.13019/) (2024)
- [Statistical Model Checking of NetLogo Models](https://mlsanity.com/paper/2509.10977/) (2025)
- [Statistical Model Checking of the Island Model: An Established Economic Agent-Based Model of Endogenous Growth](https://mlsanity.com/paper/2604.04543/) (2026)
- [A framework for quantitative modeling and analysis of highly (re)configurable systems](https://mlsanity.com/paper/1707.08411/) (2017)
- [Quantitative Security Risk Modeling and Analysis with RisQFLan](https://mlsanity.com/paper/2101.08677/) (2021)
- [Formal Analysis of Lending Pools in Decentralized Finance](https://mlsanity.com/paper/2206.01333/) (2022)
- [Testing BDI-based Multi-Agent Systems using Discrete Event Simulation](https://mlsanity.com/paper/2602.13878/) (2026)

## Abstract (arXiv)

Agent-based models (ABMs) rely on simple, explicit and reproducible rules for individual decision making, while complex collective behavior emerges from interactions among agents. Recent advances in large language models (LLMs) make it tempting to replace, enrich, or perturb these rules with LLM-based agentic capabilities. However, this raises a methodological question: how does introducing LLM-driven decisions affect the reliability, computational cost, and behavior of ABM simulations? We investigate this for Mesa ABM models, a popular Python library for ABMs, analyzed by statistical model checking. Building on Mesa's integration with the statistical model checker MultiVeStA, we extend the classical Schelling segregation model with a hybrid population: ordinary agents classify neighbors using the standard symbolic rule, while one agent delegates this task to an LLM through tool calls. The LLM-enabled agent receives natural-language descriptions of neighboring agents and invokes tools that increment counters of similar/different neighbors; these counters determine its happiness according to the original Schelling dynamics. This provides a minimal but controlled setting where the semantic, operational, and computational behavior of LLM-based decisions can be studied inside an otherwise standard ABM. We report preliminary experiments with locally served LLMs of different sizes, showing that smaller models may fail simple semantic classification experiments or become operationally unusable during repeated tool-call generation, while larger tested models pass these preliminary checks. We discuss how statistical model checking can estimate classical ABM observables and quantify the impact of introducing agentic LLM components into simulation models.