Distilling the Complexity of Agent-Based Simulations into Textual Explanations via Large Language Models

Authors

• Noé Y. Flandre, IMT Mines Alès
• Philippe J. Giabbanelli, Old Dominion UniversityFollow

Document Type

Article

Publication Date

2026

DOI

10.3390/bdcc10040121

Publication Title

Big Data and Cognitive Computing

Volume

10

Issue

4

Pages

121

Abstract

Communicating the design and results of agent-based models (ABMs) to subject matter experts is challenging, which hinders participation and limits trust in simulation-based decision support. Large language models (LLMs) can communicate ABMs as textual summaries, thus complementing traditional disclosure through statistical and visualization techniques. While prior work translated the structure of conceptual models into narratives via LLMs, our extension covers the dynamics of simulation models via an automated simulation-to-text method that extracts contextual information from NetLogo ABMs, performs repeated simulations, and generates narrative descriptions (including the model’s purpose, parameters, and simulation dynamics) using mutimodal LLMs. Furthermore, four summarization algorithms spanning abstractive and extractive methods provide shorter reports. Using Design-of-Experiments methods over three peer-reviewed ABMs, state-of-the-art multimodal LLMs from 2026 (Gemini 3.1 Pro, Qwen 3.5, Kimi K2.5, Claude Opus 4.6) and different prompt elements (e.g., roles, examples, generating insights, statistical analyses), we compare our results with several reference reports (e.g., from associate professors). We find that report quality is determined mainly (i.e., up to 34% of the variance) by the summarization algorithm and its interaction with the LLM, with abstractive summarizers (BART, T5) producing more coherent and readable reports, while Claude Opus 4.6 is the most robust LLM.

Rights

© 2026 by the authors.

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution 4.0 International (CC BY 4.0) License.

Data Availability

Article states: "To support transparency and replicability, our code is provided as a complete pipeline at https://github.com/NoeFlandre/distill-abm, accessed on 1 April 2026. All results across LLMs as well as the results of our code verification can be accessed in our storage bucket at https://huggingface.co/buckets/NoeFlandre/distill-abms-results, accessed on 1 April 2026."

Original Publication Citation

Flandre, N. Y., & Giabbanelli, P. J. (2026). Distilling the complexity of agent-based simulations into textual explanations via large language models. Big Data and Cognitive Computing, 10(4), Article 121. https://doi.org/10.3390/bdcc10040121 

ORCID

0000-0001-6816-355X (Gibbanelli)

Repository Citation

Flandre, Noé Y. and Giabbanelli, Philippe J., "Distilling the Complexity of Agent-Based Simulations into Textual Explanations via Large Language Models" (2026). VMASC Publications. 159.
https://digitalcommons.odu.edu/vmasc_pubs/159