Special Session: Large Language Model-Enhanced Evolutionary Algorithms for Industrial Optimization
Overview
Industrial systems are becoming increasingly complex due to the integration of advanced technologies, the expansion of interconnected networks, and the growing demand for higher efficiency and productivity. This complexity requires more sophisticated modeling and management strategies to ensure reliability and adaptability in dynamic environments. Industrial optimization refers to the application of various techniques aimed at improving the efficiency of processes and operations within industrial systems, with the goal of enhancing performance to make these systems more intelligent, efficient, cost-effective, and productive.
Significant progress has been made in industrial optimization within the context of evolutionary computation. While traditional evolutionary algorithms (EAs) have successfully addressed many optimization challenges in industrial intelligence, they often exhibit several limitations, such as limited generalizability, an inability to fully exploit problem-specific properties, and reliance on prior domain knowledge. Recently, large language models (LLMs) have gained considerable attention due to their success across a variety of real-world applications, including computer vision, natural language processing, and speech recognition. The application of LLMs in industrial optimization offers benefits such as enhanced predictive accuracy, improved decision-making capabilities, and greater generalizability across diverse scenarios. By leveraging these strengths, the limitations of evolutionary algorithms in industrial optimization can be mitigated.
Topics of Interest
The topics of this special session include, but are not limited to, the following:
EAs for industrial optimization focus on applying evolutionary computation techniques to solve complex optimization problems commonly encountered in industrial domains, including
workflow scheduling resource allocation power grid management energy-efficient system design route planning co-optimization of product structures and functional parameters real-time tuning of parameters in chemical or physical processes other industrial optimization problems LLM-Enhanced EAs: Developing new algorithms that integrates the capabilities of LLMs with EAs to tackle complex optimization challenges in industrial domains. This will include research in
Landscapes analysis of LLM-based evolutionary heuristic search LLM-assisted search space complexity reduction Automatic heuristic design for solving combinatorial optimization problems Automatic agent design Automatic evolutionary algorithm design Automatic algorithm design for expensive optimization LLM-driven surrogate model construction Multi-modal LLM for automatic algorithm design Multi-objective automatic algorithm design LLM Integration with Simulation Engines: Investigating methods for embedding LLMs into traditional simulation engines, enhancing their ability to predict complex system behaviors.
Real-World Application Case Studies: Conducting detailed case studies to validate the effectiveness of LLM-enhanced EAs.
Please follow the IEEE CEC 2025 Submission Website (https://www.cec2025.org/index/page.html?id=1298) to prepare and submit the paper. Special session papers are treated the same as regular conference papers. All papers accepted and presented at IEEE WCCI/CEC 2025 will be included in the conference proceedings published by IEEE Explore.
Important Dates
15 January 2025:Paper Submission Deadline 15 March 2025: Paper Acceptance Notification 1 May 2025: Final Paper Submission & Early Registration Deadline 8-12 June 2025: Conference Date
Shulei Liu
School of Artificial Intelligence, Xidian University, Xi’an, 710071, China
Email:shuleiliu@xidian.edu.cnFei Liu
Department of Computer Science, City University of Hong Kong, Hong Kong, China
Email:fliu36-c@my.cityu.edu.hkQingfu Zhang
Department of Computer Science, City University of Hong Kong, Hong Kong, China
Email:qingfu.zhang@cityu.edu.hk
