Large Language Models for Agent-Based Modelling: Current and Possible Uses Across the Modelling Cycle

Loïs Vanhée; Melania Borit; Peer Olaf Siebers; Roger Cremades; Christopher Frantz; Önder Gürcan; František Kalvas; Denisa Reshef Kera; Vivek Nallur; Kavin Narasimhan; Martin Neumann

doi:10.1007/978-3-032-31712-4_43

Large Language Models for Agent-Based Modelling: Current and Possible Uses Across the Modelling Cycle

Loïs Vanhée
, Melania Borit
, Peer Olaf Siebers
, Roger Cremades
, Christopher Frantz
, Önder Gürcan
, František Kalvas
, Denisa Reshef Kera
, Vivek Nallur
, Kavin Narasimhan
, Martin Neumann

The Graduate Program in Science, Technology and Society

Umeå University
University of Tromsø – The Arctic University of Norway
University of Nottingham
University of Leeds
Norwegian University of Science and Technology
NORCE Norwegian Research Center AS
University of West Bohemia
University College Dublin
University of Warwick
University of Southern Denmark

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The emergence of Large Language Models (LLMs) with increasingly sophisticated natural language understanding and generative capabilities has sparked interest in the Agent-based Modelling (ABM) community. With their ability to summarize, generate, analyze, categorize, transcribe and translate text, answer questions, propose explanations, sustain dialogue, extract information from unstructured text, and perform logical reasoning and problem-solving tasks, LLMs have a good potential to contribute to the modelling process. After reviewing the current use of LLMs in ABM, this study reflects on the opportunities and challenges of the potential use of LLMs in ABM. It does so by following the modelling cycle, from problem formulation to documentation and communication of model results, and holding a critical stance.

Original language	English
Title of host publication	Advances in Social Simulation - Proceedings of the 20th Social Simulation Conference
Editors	Harko Verhagen, Emile Chappin, Geeske Scholz
Publisher	Springer Science and Business Media B.V.
Pages	601-619
Number of pages	19
ISBN (Print)	9783032317117
DOIs	https://doi.org/10.1007/978-3-032-31712-4_43
State	Published - 2026
Event	20th Annual Social Simulation Conference, SSC 2025 - Delft, Netherlands Duration: 25 Aug 2025 → 29 Aug 2025

Publication series

Name	Springer Proceedings in Complexity
ISSN (Print)	2213-8684
ISSN (Electronic)	2213-8692

Conference

Conference	20th Annual Social Simulation Conference, SSC 2025
Country/Territory	Netherlands
City	Delft
Period	25/08/25 → 29/08/25

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Keywords

Agent-based Modelling Cycle
Artificial Intelligence
Large Language Models
Rapid Literature Review
Social Simulation

Access to Document

10.1007/978-3-032-31712-4_43

Cite this

Vanhée, L., Borit, M., Siebers, P. O., Cremades, R., Frantz, C., Gürcan, Ö., Kalvas, F., Kera, DR., Nallur, V., Narasimhan, K., & Neumann, M. (2026). Large Language Models for Agent-Based Modelling: Current and Possible Uses Across the Modelling Cycle. In H. Verhagen, E. Chappin, & G. Scholz (Eds.), Advances in Social Simulation - Proceedings of the 20th Social Simulation Conference (pp. 601-619). (Springer Proceedings in Complexity). Springer Science and Business Media B.V.. https://doi.org/10.1007/978-3-032-31712-4_43

Vanhée, Loïs ; Borit, Melania ; Siebers, Peer Olaf et al. / Large Language Models for Agent-Based Modelling : Current and Possible Uses Across the Modelling Cycle. Advances in Social Simulation - Proceedings of the 20th Social Simulation Conference. editor / Harko Verhagen ; Emile Chappin ; Geeske Scholz. Springer Science and Business Media B.V., 2026. pp. 601-619 (Springer Proceedings in Complexity).

@inproceedings{25c2af01175a42eab8c107852ebcaa4b,

title = "Large Language Models for Agent-Based Modelling: Current and Possible Uses Across the Modelling Cycle",

abstract = "The emergence of Large Language Models (LLMs) with increasingly sophisticated natural language understanding and generative capabilities has sparked interest in the Agent-based Modelling (ABM) community. With their ability to summarize, generate, analyze, categorize, transcribe and translate text, answer questions, propose explanations, sustain dialogue, extract information from unstructured text, and perform logical reasoning and problem-solving tasks, LLMs have a good potential to contribute to the modelling process. After reviewing the current use of LLMs in ABM, this study reflects on the opportunities and challenges of the potential use of LLMs in ABM. It does so by following the modelling cycle, from problem formulation to documentation and communication of model results, and holding a critical stance.",

keywords = "Agent-based Modelling Cycle, Artificial Intelligence, Large Language Models, Rapid Literature Review, Social Simulation",

author = "Lo{\"i}s Vanh{\'e}e and Melania Borit and Siebers, \{Peer Olaf\} and Roger Cremades and Christopher Frantz and {\"O}nder G{\"u}rcan and Franti{\v s}ek Kalvas and Denisa Reshef Kera and Vivek Nallur and Kavin Narasimhan and Martin Neumann",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; 20th Annual Social Simulation Conference, SSC 2025 ; Conference date: 25-08-2025 Through 29-08-2025",

year = "2026",

doi = "10.1007/978-3-032-31712-4\_43",

language = "אנגלית",

isbn = "9783032317117",

series = "Springer Proceedings in Complexity",

publisher = "Springer Science and Business Media B.V.",

pages = "601--619",

editor = "Harko Verhagen and Emile Chappin and Geeske Scholz",

booktitle = "Advances in Social Simulation - Proceedings of the 20th Social Simulation Conference",

}

Vanhée, L, Borit, M, Siebers, PO, Cremades, R, Frantz, C, Gürcan, Ö, Kalvas, F, Kera, DR, Nallur, V, Narasimhan, K & Neumann, M 2026, Large Language Models for Agent-Based Modelling: Current and Possible Uses Across the Modelling Cycle. in H Verhagen, E Chappin & G Scholz (eds), Advances in Social Simulation - Proceedings of the 20th Social Simulation Conference. Springer Proceedings in Complexity, Springer Science and Business Media B.V., pp. 601-619, 20th Annual Social Simulation Conference, SSC 2025, Delft, Netherlands, 25/08/25. https://doi.org/10.1007/978-3-032-31712-4_43

Large Language Models for Agent-Based Modelling: Current and Possible Uses Across the Modelling Cycle. / Vanhée, Loïs; Borit, Melania; Siebers, Peer Olaf et al.
Advances in Social Simulation - Proceedings of the 20th Social Simulation Conference. ed. / Harko Verhagen; Emile Chappin; Geeske Scholz. Springer Science and Business Media B.V., 2026. p. 601-619 (Springer Proceedings in Complexity).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Large Language Models for Agent-Based Modelling

T2 - 20th Annual Social Simulation Conference, SSC 2025

AU - Vanhée, Loïs

AU - Borit, Melania

AU - Siebers, Peer Olaf

AU - Cremades, Roger

AU - Frantz, Christopher

AU - Gürcan, Önder

AU - Kalvas, František

AU - Kera, Denisa Reshef

AU - Nallur, Vivek

AU - Narasimhan, Kavin

AU - Neumann, Martin

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

PY - 2026

Y1 - 2026

N2 - The emergence of Large Language Models (LLMs) with increasingly sophisticated natural language understanding and generative capabilities has sparked interest in the Agent-based Modelling (ABM) community. With their ability to summarize, generate, analyze, categorize, transcribe and translate text, answer questions, propose explanations, sustain dialogue, extract information from unstructured text, and perform logical reasoning and problem-solving tasks, LLMs have a good potential to contribute to the modelling process. After reviewing the current use of LLMs in ABM, this study reflects on the opportunities and challenges of the potential use of LLMs in ABM. It does so by following the modelling cycle, from problem formulation to documentation and communication of model results, and holding a critical stance.

AB - The emergence of Large Language Models (LLMs) with increasingly sophisticated natural language understanding and generative capabilities has sparked interest in the Agent-based Modelling (ABM) community. With their ability to summarize, generate, analyze, categorize, transcribe and translate text, answer questions, propose explanations, sustain dialogue, extract information from unstructured text, and perform logical reasoning and problem-solving tasks, LLMs have a good potential to contribute to the modelling process. After reviewing the current use of LLMs in ABM, this study reflects on the opportunities and challenges of the potential use of LLMs in ABM. It does so by following the modelling cycle, from problem formulation to documentation and communication of model results, and holding a critical stance.

KW - Agent-based Modelling Cycle

KW - Artificial Intelligence

KW - Large Language Models

KW - Rapid Literature Review

KW - Social Simulation

UR - https://www.scopus.com/pages/publications/105047072871

U2 - 10.1007/978-3-032-31712-4_43

DO - 10.1007/978-3-032-31712-4_43

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:105047072871

SN - 9783032317117

T3 - Springer Proceedings in Complexity

SP - 601

EP - 619

BT - Advances in Social Simulation - Proceedings of the 20th Social Simulation Conference

A2 - Verhagen, Harko

A2 - Chappin, Emile

A2 - Scholz, Geeske

PB - Springer Science and Business Media B.V.

Y2 - 25 August 2025 through 29 August 2025

ER -

Vanhée L, Borit M, Siebers PO, Cremades R, Frantz C, Gürcan Ö et al. Large Language Models for Agent-Based Modelling: Current and Possible Uses Across the Modelling Cycle. In Verhagen H, Chappin E, Scholz G, editors, Advances in Social Simulation - Proceedings of the 20th Social Simulation Conference. Springer Science and Business Media B.V. 2026. p. 601-619. (Springer Proceedings in Complexity). doi: 10.1007/978-3-032-31712-4_43