RAG/LLM Augmented Switching Driven Polymorphic Metaheuristic Framework

2025-05-20

AI Summary

Traditional metaheuristic algorithms suffer from rigid structures, strong parameter sensitivity, and premature convergence. To address these limitations, this paper proposes the Polymorphic Metaheuristic Framework (PMF). PMF introduces a real-time performance feedback–driven adaptive algorithm switching mechanism, featuring a novel performance-metric-guided intelligent switching strategy. It adopts a dual-agent collaborative architecture (PMA/PMSA) integrated with a Retrieval-Augmented Generation (RAG)-enhanced large language model (LLM) module to improve decision interpretability and generalization. Additionally, PMF incorporates dynamic exploration–exploitation balance control and multi-objective performance monitoring. Evaluated on high-dimensional, dynamic, multimodal benchmark functions, PMF achieves an average 37.6% improvement in optimization efficiency, substantially mitigates stagnation, and significantly enhances solution quality, robustness, and generalization capability.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Machine Learning: Optimization
• Multiagent Systems: Multiagent Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Metaheuristic algorithms are widely used for solving complex optimization problems, yet their effectiveness is often constrained by fixed structures and the need for extensive tuning. The Polymorphic Metaheuristic Framework (PMF) addresses this limitation by introducing a self-adaptive metaheuristic switching mechanism driven by real-time performance feedback and dynamic algorithmic selection. PMF leverages the Polymorphic Metaheuristic Agent (PMA) and the Polymorphic Metaheuristic Selection Agent (PMSA) to dynamically select and transition between metaheuristic algorithms based on key performance indicators, ensuring continuous adaptation. This approach enhances convergence speed, adaptability, and solution quality, outperforming traditional metaheuristics in high-dimensional, dynamic, and multimodal environments. Experimental results on benchmark functions demonstrate that PMF significantly improves optimization efficiency by mitigating stagnation and balancing exploration-exploitation strategies across various problem landscapes. By integrating AI-driven decision-making and self-correcting mechanisms, PMF paves the way for scalable, intelligent, and autonomous optimization frameworks, with promising applications in engineering, logistics, and complex decision-making systems.

Problem

• Enhancing metaheuristic adaptability via dynamic algorithm switching
• Improving optimization efficiency in complex problem landscapes
• Reducing stagnation and balancing exploration-exploitation strategies

Innovation

• Self-adaptive metaheuristic switching mechanism
• Dynamic algorithmic selection via performance feedback
• AI-driven decision-making for optimization