Article
Can large language models implement agent-based models? An ODD-based replication study
Ecological Modelling
— 2026 — Elsevier
Key information
Authors:
Published in
1 de julho de 2026
Abstract
Large language models (LLMs) can now synthesize non-trivial executable code from textual descriptions, raising an important question: can LLMs reliably implement agent-based models from standardized specifications in a way that supports replication, verification, and validation? We address this question by evaluating 17 contemporary LLMs on a controlled ODD-to-code translation task, using the PPHPC predator–prey model as a fully specified reference. Generated Python implementations are assessed through staged executability checks, model-independent statistical comparison against a validated NetLogo baseline, and quantitative measures of runtime efficiency and maintainability. Results show that behaviorally faithful implementations are achievable but not guaranteed, and that executability alone is insufficient for scientific use. GPT-4.1 consistently produces statistically valid and efficient implementations, with Claude 3.7 Sonnet performing well but less reliably. Overall, the findings clarify both the promise and current limitations of LLMs as model engineering tools, with implications for reproducible agent-based and ecological modeling.
Publication details
Authors in the community:
Nuno Fachada
ist145239
Carlos Miguel da Costa Fernandes
ist46419
Publication version
VoR - Version of Record
Publisher
Elsevier
Link to the publisher's version
https://doi.org/10.1016/j.ecolmodel.2026.111624
Title of the publication container
Ecological Modelling
First page or article number
111624
Volume
517
ISSN
1872-7026
Fields of Science and Technology (FOS)
computer-and-information-sciences - Computer and information sciences
Keywords
- Natural language model specification
- Specification-to-code translation
- Code generation
- Computational reproducibility
- Verification and validation
Publication language (ISO code)
eng - English
Rights type:
Restricted access
Financing entity
Fundação para a Ciência e a Tecnologia
Title of the project, award or grant: INESC INOV – Laboratório de Investigação & Desenvolvimento
Funding Stream: Avaliação UID 2023/2024
Identifier for the funding entity: https://doi.org/10.13039/501100001871
Type of identifier of the funding entity: Crossref Funder
Number for the project, award or grant: UID/06486/2025
Financing entity
Fundação para a Ciência e a Tecnologia
Title of the project, award or grant: INESC INOV – Laboratório de Investigação & Desenvolvimento
Funding Stream: Avaliação UID 2023/2024 PRR
Identifier for the funding entity: https://doi.org/10.13039/501100001871
Type of identifier of the funding entity: Crossref Funder
Number for the project, award or grant: UID/PRR/06486/2025
Financing entity
Fundação para a Ciência e a Tecnologia
Title of the project, award or grant: INESC INOV – Laboratório de Investigação & Desenvolvimento
Funding Stream: EQUIPAR +2 - UID.PRR2
Identifier for the funding entity: https://doi.org/10.13039/501100001871
Type of identifier of the funding entity: Crossref Funder
Number for the project, award or grant: UID/PRR2/06486/2025
Financing entity
Fundação para a Ciência e a Tecnologia
Title of the project, award or grant: Instituto de Telecomunicações
Funding Stream: Avaliação UID 2023/2024
Identifier for the funding entity: https://doi.org/10.13039/501100001871
Type of identifier of the funding entity: Crossref Funder
Number for the project, award or grant: UID/50008/2025
Financing entity
Fundação para a Ciência e a Tecnologia
Title of the project, award or grant: Instituto de Telecomunicações
Funding Stream: Avaliação UID 2023/2024 PRR
Identifier for the funding entity: https://doi.org/10.13039/501100001871
Type of identifier of the funding entity: Crossref Funder
Number for the project, award or grant: UID/PRR/50008/2025
Financing entity
Fundação para a Ciência e a Tecnologia
Title of the project, award or grant: Instituto de Telecomunicações
Funding Stream: EQUIPAR +2 - UID.PRR2
Identifier for the funding entity: https://doi.org/10.13039/501100001871
Type of identifier of the funding entity: Crossref Funder
Number for the project, award or grant: UID/PRR2/50008/2025
Financing entity
Fundação para a Ciência e a Tecnologia
Title of the project, award or grant: João P. Matos-Carvalho
Identifier for the funding entity: https://doi.org/10.13039/501100001871
Type of identifier of the funding entity: Crossref Funder
Number for the project, award or grant: 2023.15441.TENURE.051/CP00003/CT00029
Financing entity
Fundação para a Ciência e a Tecnologia
Title of the project, award or grant: LASIGE Centro de Investigação em Ciência e Engenharia da Computação
Funding Stream: Avaliação UID 2023/2024
Identifier for the funding entity: https://doi.org/10.13039/501100001871
Type of identifier of the funding entity: Crossref Funder
Number for the project, award or grant: UID/00408/2025
Financing entity
Fundação para a Ciência e a Tecnologia
Title of the project, award or grant: LASIGE Centro de Investigação em Ciência e Engenharia da Computação
Funding Stream: Avaliação UID 2023/2024 PRR
Identifier for the funding entity: https://doi.org/10.13039/501100001871
Type of identifier of the funding entity: Crossref Funder
Number for the project, award or grant: UID/PRR/00408/2025
Financing entity
Fundação para a Ciência e a Tecnologia
Title of the project, award or grant: A computational pipeline for modeling and predicting wildfire behavior
Funding Stream: CEEC INST 2ed
Identifier for the funding entity: https://doi.org/10.13039/501100001871
Type of identifier of the funding entity: Crossref Funder
Number for the project, award or grant: CEECINST/00002/2021/CP2788/CT0001
Financing entity
Instituto Lusófono de Investigação e Desenvolvimento
Title of the project, award or grant: FireGuard: Fire Management with Autonomous UAV Navigation
Funding Stream: Seed Funding
Identifier for the funding entity: http://isni.org/isni/0000000458956849
Type of identifier of the funding entity: ISNI
Number for the project, award or grant: COFAC/ILIND/COPELABS/1/2024
Financing entity
Ministerio de Ciencia, Innovación y Universidades
Title of the project, award or grant: SINTESIS Y EXPLORACION DE SISTEMAS COMPLEJOS EFICIENTES APLICADAS A CIBERSEGURIDAD, VIDEOJUEGOS Y ANALISIS DE SOCIEDADES HISTORICAS
Funding Stream: MICIU/AEI/10.13039/501100011033
Identifier for the funding entity: https://doi.org/10.13039/100014440
Type of identifier of the funding entity: Crossref Funder
Number for the project, award or grant: PID2023-147409NB-C21