Aug 2026· International Conference on Advanced Computational Intelligence· pp. 218-225· 0 citations· 22 references
Abstract
Adaptively adjusting the components or parameters of decomposition-based multiobjective evolutionary algorithms (MOEA/Ds) is crucial for enhancing its performance in handling multiobjective optimization problems with complex Pareto fronts. However, component design strategies and parameter tuning mechanisms based on domain knowledge remain the primary bottleneck limiting performance improvement. This paper proposes a large language model (LLM)-enhanced MOEA/D algorithm. The algorithm leverages LLM’s domain priors and prompt engineering techniques to automatically generate modular code, replacing manually designed search operators. Furthermore, by reasoning about the algorithm’s iterative process information, it achieves adaptive dynamic adjustments of the aggregation function, weight strategy, and parameter rules. Experimental results on 12 benchmark test instances with complex Pareto fronts demonstrate that the proposed LLM-driven MOEA/D variant exhibits significant advantages over traditional methods in the HV performance metric.
This paper includes new mutation techniques with a Pareto-based differential evolution algorithm, leveraging Generative AI to increase candidate solution diversity and a non-dominated sorting technique to lower the computational complexity involved in Pareto dominance.
Sunil Kumar Gouda, S. Ramasubbareddy, Kumar Surjeet Chaudhury et al.· Scientific Reports· 0 citations
Experimental results demonstrate that LLMDE achieves competitive performance on the benchmark suite while continuously generating high-quality solutions for complex constrained optimization tasks, and successfully demonstrate the viability of embedding LLMs within metaheuristics, paving a promising path toward the desi...
Rong-Mu Chai, V. Snášel, Xiao-Peng Wang et al.· 0 citations
Surrogate models constitute a promising approach for scaling multi-objective architecture optimization to larger spaces and complex architectural models and maintain the Pareto front quality provided by evolutionary algorithms.
J. A. Díaz-Pace, Daniele Di Pompeo, Antonela Tommasel· 0 citations
The proposed Multi-Objective Narwhal Optimizer (MONO), a Pareto-based extension of the recently developed Narwhal Optimizer, incorporates Pareto dominance, external archive management, adaptive multi-leader guidance, and crowding-distance-based diversity preservation to effectively balance convergence and exploration t...
S. Medjahed, Mourad Bouatouche, Fatima Boukhatem· Journal of Supercomputing· 0 citations
Results confirm that embedding hyper-heuristic mechanisms within expert systems provides a powerful approach for addressing complex optimization problems, paving the way for scalable and data-driven intelligent decision-support systems.
To address the trade-off between production efficiency and sustainable manufacturing, this study investigates the green flexible job shop scheduling problem (GFJSP) by simultaneously minimizing makespan and total energy consumption. An improved decomposition-based multi-objective evolutionary algorithm (IMOEA/D) is pro...
