ArchEvolve: A Collaborative and Interactive Search-Based Framework with Preference Learning for Optimizing Software Architectures

Ayobami E. Mesioye; Adesola M. Falade; Kayode E. Akinola

doi:10.62411/jcta.14990

Authors

Ayobami E. Mesioye McPherson University
Adesola M. Falade McPherson University
Kayode E. Akinola McPherson University

DOI:

https://doi.org/10.62411/jcta.14990

Keywords:

Collaborative Decision-Making, Cooperative Coevolution, Human-in-the-Loop Optimization, Interactive Evolutionary Computation, Multi-Objective Optimization, Preference Learning, Search-Based Software Engineering (SBSE), Software Architecture

Abstract

The use of Search-Based Software Engineering (SBSE) for optimizing software architecture has evolved from fully automated to interactive approaches, integrating human expertise. However, current interactive tools face limitations: they typically support only single decision-makers, confine architects to passive roles, and induce significant cognitive fatigue from repetitive evaluations. These issues disconnect them from modern, team-based software development, where collaboration and consensus are crucial. To address these shortcomings, we propose "ArchEvolve," a novel framework designed to facilitate collaborative, multi-architect decision-making. ArchEvolve employs a cooperative coevolutionary model that concurrently evolves a population of candidate architectures and distinct populations representing each architect's unique preferences. This structure guides the search towards high-quality consensus solutions that accommodate diverse, often conflicting, stakeholder viewpoints. An integrated Artificial Neural Network (ANN) serves as a preference learning module, trained on explicit team feedback to act as a surrogate evaluator. This active learning cycle substantially reduces the number of required human interactions and alleviates user fatigue. Empirical evaluation on two industrial case studies (E-Commerce System and Healthcare Management System) compared ArchEvolve to a state-of-the-art interactive baseline. Results indicate that ArchEvolve achieves statistically significant improvements in both solution quality and consensus-building. The preference learning module demonstrated over 90% accuracy in predicting team ratings and reduced human evaluations by up to 46% without compromising final solution quality. ArchEvolve provides a practical, scalable framework supporting collaborative, consensus-driven architectural design, making interactive optimization a more viable and efficient tool for real-world software engineering teams by intelligently integrating cooperative coevolutionary search with a preference learning surrogate.

Author Biographies

Ayobami E. Mesioye, McPherson University

Department of Cybersecurity, McPherson University, Seriki Sotayo, Ogun State 110106, Nigeria

Adesola M. Falade, McPherson University

Department of Software Engineering, McPherson University, Seriki Sotayo, Ogun State 110106, Nigeria

Kayode E. Akinola, McPherson University

Department of Information Technology, McPherson University, Seriki Sotayo, Ogun State 110106, Nigeria

References

P. Clements, D. Garlan, R. Little, R. Nord, and J. Stafford, Documenting software architectures: views and beyond, 2nd ed. Boston: Pearson Education, 2010.

A. Mohamed and M. Zulkernine, “Architectural Design Decisions for Achieving Reliable Software Systems,” in Architecting Critical Systems, 2010, pp. 19–32. doi: 10.1007/978-3-642-13556-9_2.

A. El Murabet and A. Abtoy, “Methodologies of the Validation of Software Architectures,” J. Comput. Theor. Appl., vol. 1, no. 2, pp. 29–36, 2023, doi: 10.33633/jcta.v1i2.9332.

L. Dobrica, “Exploring Approaches of Integration Software Architecture Modeling with Quality Analysis Models,” in 2011 Ninth Working IEEE/IFIP Conference on Software Architecture, Jun. 2011, pp. 113–122. doi: 10.1109/WICSA.2011.23.

O. Sievi-Korte, I. Richardson, and S. Beecham, “Software architecture design in global software development: An empirical study,” J. Syst. Softw., vol. 158, p. 110400, Dec. 2019, doi: 10.1016/j.jss.2019.110400.

S. R. V and H. Muccini, “Group decision-making in software architecture: A study on industrial practices,” Inf. Softw. Technol., vol. 101, pp. 51–63, Sep. 2018, doi: 10.1016/j.infsof.2018.04.009.

M. Ö. Demir, O. Chouseinoglou, and A. K. Tarhan, “Factors affecting architectural decision‐making process and challenges in software projects: An industrial survey,” J. Softw. Evol. Process, vol. 36, no. 10, Oct. 2024, doi: 10.1002/smr.2703.

M. Harman, P. McMinn, J. T. de Souza, and S. Yoo, “Search Based Software Engineering: Techniques, Taxonomy, Tutorial,” in Empirical Software Engineering and Verification, 2012, pp. 1–59. doi: 10.1007/978-3-642-25231-0_1.

J. Zhao, H. Zhang, H. Yu, H. Fei, X. Huang, and Q. Yang, “A many-objective evolutionary algorithm based on three states for solving many-objective optimization problem,” Sci. Rep., vol. 14, no. 1, p. 19140, Aug. 2024, doi: 10.1038/s41598-024-70145-8.

M. Harman, “The Current State and Future of Search Based Software Engineering,” in Future of Software Engineering (FOSE ’07), May 2007, pp. 342–357. doi: 10.1109/FOSE.2007.29.

S. Dasanayake, J. Markkula, S. Aaramaa, and M. Oivo, “An Empirical Study on Collaborative Architecture Decision Making in Software Teams,” in Software Architecture, 2016, pp. 238–246. doi: 10.1007/978-3-319-48992-6_18.

A. Ramirez, J. R. Romero, and C. L. Simons, “A Systematic Review of Interaction in Search-Based Software Engineering,” IEEE Trans. Softw. Eng., vol. 45, no. 8, pp. 760–781, Aug. 2019, doi: 10.1109/TSE.2018.2803055.

T. Houichime and Y. El Amrani, “Optimized design refactoring (ODR): a generic framework for automated search-based refactoring to optimize object-oriented software architectures,” Autom. Softw. Eng., vol. 31, no. 2, p. 48, Nov. 2024, doi: 10.1007/s10515-024-00446-9.

M. Babar, S. Azeem, and F. Arif, “Integration of Security Non-Functional Requirements and Architectural Design: A Comparative Analysis,” Int. J. Secur. Its Appl., vol. 11, no. 10, pp. 45–54, Oct. 2017, doi: 10.14257/ijsia.2017.11.10.05.

W. Lou et al., “Unleashing Network/Accelerator Co-Exploration Potential on FPGAs: A Deeper Joint Search,” IEEE Trans. Comput. Des. Integr. Circuits Syst., vol. 43, no. 10, pp. 3041–3054, Oct. 2024, doi: 10.1109/TCAD.2024.3391688.

H. Aljawawdeh, “An interactive metaheuristic search framework for software service identification from business process models,” The University of the West of England, 2019. [Online]. Available: https://uwe-repository.worktribe.com/output/853842

A. Rago, S. Vidal, J. A. Diaz-Pace, S. Frank, and A. van Hoorn, “Distributed quality-attribute optimization of software architectures,” in Proceedings of the 11th Brazilian Symposium on Software Components, Architectures, and Reuse, Sep. 2017, pp. 1–10. doi: 10.1145/3132498.3132509.

W. Freire, C. Rosa, A. Amaral, and T. Colanzi, “Validating an Interactive Ranking Operator for NSGA-II to Support the Opti-mization of Software Engineering Problems,” in Proceedings of the XXXVI Brazilian Symposium on Software Engineering, Oct. 2022, pp. 337–346. doi: 10.1145/3555228.3555232.

C. V. Bindewald, W. M. Freire, A. M. M. M. Amaral, and T. E. Colanzi, “Towards the support of user preferences in search-based product line architecture design,” in Proceedings of the XXXIII Brazilian Symposium on Software Engineering, Sep. 2019, pp. 387–396. doi: 10.1145/3350768.3351993.

C. V. Bindewald, W. M. Freire, A. M. M. M. Amaral, and T. E. Colanzi, “Supporting user preferences in search-based product line architecture design using Machine Learning,” in Proceedings of the 14th Brazilian Symposium on Software Components, Architectures, and Reuse, Oct. 2020, pp. 11–20. doi: 10.1145/3425269.3425278.

A. Hamza, W. Hussain, H. Iftikhar, A. Ahmad, and A. M. Shamim, “Evaluating Open-Source Machine Learning Project Quality Using SMOTE-Enhanced and Explainable ML/DL Models,” J. Comput. Theor. Appl., vol. 3, no. 2, pp. 206–222, Nov. 2025, doi: 10.62411/jcta.14793.

F. H. Kuviatkovski, W. M. Freire, A. M. M. M. Amaral, T. E. Colanzi, and V. D. Feltrim, “Evaluating Machine Learning Algorithms in Representing Decision Makers in search-based PLA,” in 2022 IEEE 19th International Conference on Software Architecture Companion (ICSA-C), Mar. 2022, pp. 68–75. doi: 10.1109/ICSA-C54293.2022.00057.

C. Arasaki, L. Wolschick, W. Freire, and A. Amaral, “Feature selection in an interactive search-based PLA design approach,” in Proceedings of the 17th Brazilian Symposium on Software Components, Architectures, and Reuse, Sep. 2023, pp. 11–20. doi: 10.1145/3622748.3622750.

C. A. Akiotu et al., “A Predictive Nutritional Assessment System for Vegetarians using Artificial Neural Networks,” J. Futur. Artif. Intell. Technol., vol. 2, no. 2, pp. 294–312, Aug. 2025, doi: 10.62411/faith.3048-3719-117.

K. Yang, M. Emmerich, A. Deutz, and T. Bäck, “Multi-Objective Bayesian Global Optimization using expected hypervolume improvement gradient,” Swarm Evol. Comput., vol. 44, pp. 945–956, Feb. 2019, doi: 10.1016/j.swevo.2018.10.007.

J. Goers and G. Horton, “On the Combinatorial Acceptability Entropy Consensus Metric for Multi-Criteria Group Decisions,” Gr. Decis. Negot., vol. 33, no. 5, pp. 1247–1268, Oct. 2024, doi: 10.1007/s10726-024-09891-z.