EUVIMEDEUVIMED entdecken
Crossref

Can large language models implement agent-based models? An ODD-based replication study

Nuno Fachada, Daniel Fernandes, Carlos M. Fernandes, João P. Matos-Carvalho

Ecological Modelling · 2026-07 · 517 · 111624

DOI: 10.1016/j.ecolmodel.2026.111624 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ecological Modelling, 2026-07. Verfasst von Nuno Fachada und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 78 Literaturangaben. Gefördert von: Universidade Lusófona, Spain Ministry of Science Innovation and Universities, Foundation for Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • Universidade Lusófona
  • Spain Ministry of Science Innovation and Universities
  • Foundation for Science and Technology

Zitieren

APA

Fachada, N., Fernandes, D., Fernandes, C. M., & Matos-Carvalho, J. P. (2026). Can large language models implement agent-based models? An ODD-based replication study. Ecological Modelling, 517, 111624. https://doi.org/10.1016/j.ecolmodel.2026.111624

Vancouver

Fachada N, Fernandes D, Fernandes CM, Matos-Carvalho JP. Can large language models implement agent-based models? An ODD-based replication study. Ecological Modelling. 2026;517:111624. doi:10.1016/j.ecolmodel.2026.111624

BibTeX
@article{Fachada2026,
  author = {Fachada, Nuno and Fernandes, Daniel and Fernandes, Carlos M. and Matos-Carvalho, João P.},
  title = {Can large language models implement agent-based models? An ODD-based replication study},
  journal = {Ecological Modelling},
  year = {2026},
  volume = {517},
  pages = {111624},
  doi = {10.1016/j.ecolmodel.2026.111624}
}
Kostenlos starten →