Unleashing the Potential of Large Language Models for Dynamic Multiobjective Optimization
Contribution
Recasts dynamic multiobjective optimization as a prompt-guided time-series prediction problem and shows that large language models can generate competitive solutions.
Abstract
To address these challenges, this work introduces a novel approach for DMOPs using large language models (LLMs). Specifically, we reformulate the solution prediction in DMOPs as a time-series prediction problem and guide the LLMs to predict solutions using four carefully crafted prompts.
Why This Paper Matters
This paper opens a new line of work at the intersection of LLMs and dynamic multiobjective optimization, moving beyond handcrafted transfer heuristics toward prompt-based prediction.
When You May Find This Relevant
Cite this when discussing LLM-assisted dynamic optimization, prompt-based solution prediction, or emerging hybrid optimization frameworks.
- When using large language models for dynamic multiobjective optimization
- When framing dynamic optimization as a prompt-guided prediction task
BibTeX
@article{jiang2026unleashing,
title={Unleashing the Potential of Large Language Models for Dynamic Multiobjective Optimization},
author={Jiang, Min and Wu, Huolong and Wang, Zhenzhong and Yen, Gary G.},
journal={IEEE Transactions on Emerging Topics in Computational Intelligence},
pages={1--12},
year={2026},
doi={10.1109/tetci.2026.3683702},
publisher={IEEE},
}