From Conceptual Model to Empirical Validation: A Refined Decision Framework for Hybrid Simulation–Machine Learning–Optimization Architectures in Complex Systems

Authors

https://doi.org/10.22105/opt.vi.114

Abstract

Optimizing complex systems, like supply chains and manufacturing, is a tough task. The problem is that detailed simulations are too expensive to use for repeated optimization. To solve this, three main approaches have emerged: using heuristics with simulation, optimization with surrogates, and reinforcement learning. Previous work created a model to choose the right approach based on the problem, but it was just a concept and hadn't been tested. Also, it didn't consider the new role of Large Language Models (LLMs) in optimization. This study fills these gaps. We reviewed research from 2019 to 2025 to understand the key features of complex system optimization and how well each approach works. Then, we proposed a new approach, LLM-guided surrogate-assisted optimization, which uses a LLM to turn problem descriptions into smart initial sampling strategies, add domain knowledge to surrogates, and narrow down the search space using textual constraints. We mathematically defined this new approach, added it to a decision tree, and tested it in three areas: aerodynamic design, water distribution, and PID controller tuning. Our results show that choosing the right approach based on problem attributes works better than picking one randomly, and our new approach is more efficient when textual domain knowledge is available. This means we can optimize complex systems more effectively, which is a big deal for many industries. By using the right tools for the job, we can make better decisions and improve performance. Our study provides a roadmap for doing just that.

Keywords:

Simulation-based optimization, Surrogate modeling, Metaheuristics, Reinforcement learning, Large language models, Complex systems, Decision framework, LLM-guided optimization

References

  1. [1] Attar, A., Raissi, S., & Khalili-Damghani, K. (2017). A simulation-based optimization approach for free distributed repairable multi-state availability-redundancy allocation problems. Reliability engineering & system safety, 157, 177–191. https://doi.org/10.1016/j.ress.2016.09.006
  2. [2] Abdul, A. S. (2024). Skew variation analysis in distributed battery management systems using CAN FD and chained SPI for 192-cell architectures. Journal of electrical systems, 20, 3109–3117. https://www.academia.edu/144761350
  3. [3] Forsberg, L., Vance, S., Okeke, A., & Mabel, E. (2026). From algorithms to applications: Simulation-based and machine learning approaches to complex system optimization. Journal of information systems engineering and management, 11(1s), 383–392. https://doi.org/10.55267/jisem.2026.18370654
  4. [4] Ranković, B., & Schwaller, P. (2026). Large language models as generative Bayesian policies. https://arxiv.org/abs/2601.XXXXX
  5. [5] Khaniki, M. A. L., Taroodi, F., & Safizadeh, B. (2025). A novel multi-timescale stability-preserving hierarchical reinforcement learning controller framework for adaptive control in high-dimensional dynamical systems. https://doi.org/10.48550/arXiv.2510.22420
  6. [6] Fathi, M., Khakifirooz, M., & Pardalos, P. M. (2019). Optimization in large scale problems: Industry 4.0 and Society 5.0 applications (Vol. 152). Springer. https://doi.org/10.1007/978-3-030-28565-4
  7. [7] Candelieri, A., Perego, R., & Archetti, F. (2018). Bayesian optimization of pump operations in water distribution systems. Journal of global optimization, 71(1), 213–235. https://doi.org/10.1007/s10898-018-0641-2
  8. [8] Yalçin, O., Canli, A., Yilmaz, A. R., & Erkmen, B. (2022). Robust tuning of pid controller using differential evolution algorithm based on fpga. 2022 9th international conference on electrical and electronics engineering (ICEEE) (pp. 180–184). IEEE. https://doi.org/10.1109/ICEEE55327.2022.9772529
  9. [9] Bussemaker, J. H., Saves, P., Bartoli, N., Lefebvre, T., & Lafage, R. (2025). System architecture optimization strategies: dealing with expensive hierarchical problems. Journal of global optimization, 91(4), 851–895. https://doi.org/10.1007/s10898-024-01443-8
  10. [10] Carson, J. S. (2002). Model verification and validation. Proceedings of the winter simulation conference (Vol. 1, pp. 52–58). IEEE. https://doi.org/10.1109/WSC.2002.1172868
  11. [11] Feurer, M., Klein, A., Eggensperger, K., Springenberg, J., Blum, M., & Hutter, F. (2015). Efficient and robust automated machine learning. Advances in neural information processing systems (Vol. 28). Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2015/file/11d0e6287202fced83f79975ec59a3a6-Paper.pdf
  12. [12] Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., … & Amodei, D. (2020). Language models are few-shot learners. Advances in neural information processing systems (Vol. 33, pp. 1877–1901). Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
  13. [13] Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E. (2023). Sparks of artificial general intelligence: Early experiments with GPT-4. https://arxiv.org/abs/2303.12712
  14. [14] Aglietti, V., Ktena, I., & Gal, Y. (2024). Kernel structure discovery via large language models. https://arxiv.org/abs/2402.XXXXX
  15. [15] Fu, M. C. (2015). Handbook of simulation optimization (Vol. 216). Springer. https://doi.org/10.1007/978-1-4939-1384-8
  16. [16] Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and psychological measurement, 20(1), 37–46. https://doi.org/10.1177/001316446002000104
  17. [17] Forrester, A., Sobester, A., & Keane, A. (2008). Engineering design via surrogate modelling: A practical guide. John Wiley & Sons. https://doi.org/10.1002/9780470770801
  18. [18] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. KDD ’16: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785–794). Association for Computing Machinery. https://doi.org/10.1145/2939672.2939785
  19. [19] Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence, 35(8), 1798–1828. https://doi.org/10.1109/TPAMI.2013.50
  20. [20] Williams, C. K. I., & Rasmussen, C. E. (2006). Gaussian processes for machine learning (Vol. 2). MIT press Cambridge, MA. https://doi.org/10.1142/S0129065704001899
  21. [21] Sutton, R. S., Barto, A. G., & Barto, A. (1998). Reinforcement learning: An introduction. MIT press Cambridge. https://doi.org/10.1017/S0263574799271172
  22. [22] Yang, C., Wang, X., Lu, Y., Liu, H., Le, Q. V, Zhou, D., & Chen, X. (2024). Large language models as optimizers. International conference on learning representations (Vol. 2024, pp. 12028–12068). ICLR Proceedings. https://proceedings.iclr.cc/paper_files/paper/2024/file/3339f19c5fcee3ad74502947a32be9e6-Paper-Conference.pdf
  23. [23] Hutter, F., Hoos, H. H., & Leyton-Brown, K. (2011). Sequential model-based optimization for general algorithm configuration. Learning and intelligent optimization (pp. 507–523). Berlin, Heidelberg: Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-25566-3_40
  24. [24] Queipo, N. V, Haftka, R. T., Shyy, W., Goel, T., Vaidyanathan, R., & Kevin Tucker, P. (2005). Surrogate-based analysis and optimization. Progress in aerospace sciences, 41(1), 1–28. https://doi.org/10.1016/j.paerosci.2005.02.001
  25. [25] dos Santos Coelho, L., & Mariani, V. C. (2012). Firefly algorithm approach based on chaotic Tinkerbell map applied to multivariable PID controller tuning. Computers & mathematics with applications, 64(8), 2371–2382. https://doi.org/10.1016/j.camwa.2012.05.007
  26. [26] Juan, A. A., Faulin, J., Grasman, S. E., Rabe, M., & Figueira, G. (2015). A review of simheuristics: Extending metaheuristics to deal with stochastic combinatorial optimization problems. Operations research perspectives, 2, 62–72. https://doi.org/10.1016/j.orp.2015.03.001
  27. [27] Cai, X., Gao, L., Li, X., & Qiu, H. (2019). Surrogate-guided differential evolution algorithm for high dimensional expensive problems. Swarm and evolutionary computation, 48, 288–311. https://doi.org/10.1016/j.swevo.2019.04.009
  28. [28] Wang, Q., Zhang, Y., Gong, D., Song, X., He, C., Ji, X., & Chu, F. (2026). A review of surrogate-assisted evolutionary multi-objective optimization. IEEE transactions on emerging topics in computational intelligence, 10(4), 2741–2761. https://doi.org/10.1109/TETCI.2026.3670690
  29. [29] Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021). Physics-informed machine learning. Nature reviews physics, 3(6), 422–440. https://doi.org/10.1038/s42254-021-00314-5
  30. [30] Grimm, V., Berger, U., DeAngelis, D. L., Polhill, J. G., Giske, J., & Railsback, S. F. (2010). The ODD protocol: A review and first update. Ecological modelling, 221(23), 2760–2768. https://doi.org/10.1016/j.ecolmodel.2010.08.019

Downloads

Published

2026-06-23

Issue

Vol. 3 No. 2 (2026): Optimality

Section

Articles

License

Copyright (c) 2024 Optimality

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Montazeri, F. Z. (2026). From Conceptual Model to Empirical Validation: A Refined Decision Framework for Hybrid Simulation–Machine Learning–Optimization Architectures in Complex Systems. Optimality, 3(2), 186-200. https://doi.org/10.22105/opt.vi.114

Similar Articles

1-10 of 51

You may also start an advanced similarity search for this article.