Autonomous Multiobjective Optimization Using Large Language Model
- 15 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 30 (2) , 594-608
Abstract
Multi-objective optimization problems (MOPs) are ubiquitous in real-world applications, presenting a complex challenge of balancing multiple conflicting objectives. Traditional multi-objective evolutionary algorithms (MOEAs), though effective, often rely on domain-specific expertise for improved optimization performance, hindering adaptability to unseen MOPs. In recent years, the Large Language Models (LLMs) has revolutionized software engineering by enabling the autonomous generation and refinement of programs. Leveraging this breakthrough, we propose a new LLM-based framework that autonomously designs MOEAs for solving MOPs. The proposed framework includes a robust testing module to refine the generated MOEA through error-driven dialogue with LLMs, a dynamic selection strategy along with informative prompting-based crossover and mutation to fit textual optimization pipeline. Our approach facilitates the design of MOEA without the extensive demands for expert intervention, thereby speeding up the innovation of MOEA. Empirical studies across various MOP categories validate the robustness and superior performance of our proposed framework.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2022YFC3801700)
- National Natural Science Foundation of China (U21A20512)
- Key Research and Development Program of Heilongjiang (2022YFC3801700)
- Key Research and Development Program of Heilongjiang (U21A20512)
This publication has 46 references indexed in Scilit:
- Understanding the Importance of Evolutionary Search in Automated Heuristic Design with Large Language Models2024
- Large Language Model Assisted Software Engineering: Prospects, Challenges, and a Case Study2023
- Evolution Through Large Models2023
- Solving Multi-objective Traveling Salesman Problem2023
- Dynamic Programming Approach to Solve Real-World Application of Multi-Objective Unbounded Knapsack Problem2023
- A Mixed-Factor Evolutionary Algorithm for Multi-objective Knapsack Problem2022
- Multi-objective traveling salesman problem: an ABC approachApplied Intelligence, 2020
- Evolutionary AlgorithmsWIREs Data Mining and Knowledge Discovery, 2014
- Comparison between MOEA/D and NSGA-II on the Multi-Objective Travelling Salesman Problem2009
- Evolutionary multi-objective portfolio optimization in practical contextInternational Journal of Automation and Computing, 2008