[2602.10140] Can Large Language Models Implement Agent-Based Models? An ODD-based Replication Study

Computer Science > Software Engineering arXiv:2602.10140 (cs) [Submitted on 8 Feb 2026 (v1), last revised 30 Apr 2026 (this version, v2)] Title:Can Large Language Models Implement Agent-Based Models? An ODD-based Replication Study Authors:Nuno Fachada, Daniel Fernandes, Carlos M. Fernandes, João P. Matos-Carvalho View a PDF of the paper titled Can Large Language Models Implement Agent-Based Models? An ODD-based Replication Study, by Nuno Fachada and 3 other authors View PDF HTML (experimental) 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, ...