Evo Code Graph: A Self-Adaptive Evolutionary Graph Reasoning Architecture for Intelligent Software Engineering
Keywords:
Evo Code Graph, evolutionary computing, graph reasoning, intelligent software engineeringAbstract
The increasing complexity of modern software systems has created a need for intelligent engineering approaches capable of reasoning over heterogeneous, interconnected, and continuously changing software artifacts. Conventional code-analysis and generation approaches frequently treat source files, dependencies, requirements, tests, and architectural components as relatively independent entities, limiting their ability to model structural relationships and adapt reasoning strategies to changing development conditions. This paper proposes EvoCodeGraph, a self-adaptive evolutionary graph reasoning architecture for intelligent software engineering. The proposed architecture conceptually integrates software knowledge representation through graph structures with evolutionary adaptation mechanisms and reasoning-oriented code intelligence. Its design is theoretically positioned around the evolutionary graph-reasoning paradigm presented by Ramamurthy, Konduru, and Amanmadov (2026), while extending that conceptual direction toward a broader architecture for adaptive software engineering. The methodology defines interconnected software graphs, graph-aware reasoning, evolutionary candidate generation, fitness-based evaluation, adaptive strategy selection, and feedback-driven refinement. The resulting framework is designed to support software comprehension, code generation, defect-oriented reasoning, dependency analysis, refactoring, and adaptive maintenance. Analytical findings indicate that the principal value of EvoCodeGraph lies not merely in representing code as a graph, but in coupling graph structure with an iterative adaptation mechanism that can modify reasoning behavior according to software context. The paper further identifies computational overhead, graph-scale management, fitness-design challenges, and explainability as important limitations. Overall, EvoCodeGraph provides a research-oriented architecture for integrating structural software knowledge, evolutionary optimization, and adaptive reasoning into a unified intelligent software engineering framework.
Downloads
References
1. K. Ramamurthy, R. K. Konduru and N. Amanmadov, "EvoGraphCoder: An Evolutionary Graph-Reasoning Framework for Self-Adaptive Software Engineering," in IEEE Access, vol. 14, pp. 63063-63076, 2026, doi: 10.1109/ACCESS.2026.3686019.
2. M. -Y. Ameca-Alducin, E. Mezura-Montes and N. Cruz-Ramírez, “A repair method for differential evolution with combined variants to solve dynamic constrained optimization problems,” in Proc. of Genetic and Evolutionary Computation Conf. (GECCO), New York, NY, USA, pp. 241–248, 2015.
3. M. R. Bonyadi and Z. Michalewicz, “On the edge of feasibility: A case study of the particle swarm optimizer,” in Proc. IEEE Congress on Evolutionary Computation (CEC), Beijing, China, pp. 3059–3066, 2014.
4. J. Branke, “Evolutionary optimization in dynamic environments,” in Genetic Algorithms and Evolutionary Computation, vol. 3. New York, NY, USA: Springer, 2012.
5. H. Richter and F. Dietel, “Solving dynamic constrained optimization problems with asynchronous change pattern,” in Proc. European Conf. on the Applications of Evolutionary Computation, Torino, Italy, pp. 334–343, 2011.
6. H. Richter, “Memory design for constrained dynamic optimization problems,” in European Conf. on the Applications of Evolutionary Computation, Istanbul, Turkey, pp. 552–561, 2010.
7. H. Richter and S. Yang, “Memory based on abstraction for dynamic fitness functions,” in Workshops on Applications of Evolutionary Computation, Naples, Italy, pp. 596–605, 2008.
8. H. K. Singh, A. Isaacs, T. T. Nguyen, T. Ray and X. Yao, “Performance of infeasibility driven evolutionary algorithm (IDEA) on constrained dynamic single objective optimization problems,” in Proc. IEEE Congress on Evolutionary Computation (CEC), Trondheim, Norway, pp. 3127–3134, 2009.
9. D. Yazdani, M. N. Omidvar, J. Branke, T. T. Nguyen and X. Yao, “Scaling up dynamic optimization problems: A divide-and-conquer approach,” IEEE Transactions on Evolutionary Computation, vol. 24, no. 1, pp. 1–15, 2019.
10. F. Zaman, S. Elsayed, R. Sarker, D. Essam and C. A. C. Coello, “Pro-reactive approach for project scheduling under unpredictable disruptions,” IEEE Transactions on Cybernetics, pp. 1–14, 2021.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Farhana Islam (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published by The Parthenon Frontiers and its associated journals are distributed under the terms of the Creative Commons Attribution (CC BY 4.0) International License unless otherwise stated.
Authors retain full copyright of their published work. By submitting their manuscript, authors agree to grant The Parthenon Frontiers a non-exclusive license to publish, archive, and distribute the article worldwide. Authors are free to:
-
Share their article on personal websites, institutional repositories, or social media platforms.
-
Reuse their content in future works, presentations, or educational materials, provided proper citation of the original publication.
