Modeling Contexts in Trade-off Total Cost and Customer Satisfaction VRP via Large Language Models

作者：Hong-Wei Ding, Zhen-Song Chen, Yi Yang, Weiping Ding · 发表于：IEEE transactions on fuzzy systems · 年份：2026 · DOI：10.1109/TFUZZ.2025.3621215 · 研究领域：Computer Science

The vehicle routing problem (VRP) is among the most extensively studied combinatorial optimization problems in operations research. As a critical variant, the sustainable VRP (SVRP) integrates multidimensional cost considerations, including environmental, economic, and social dimensions. When modeling optimization problems, it is crucial to acknowledge that decision-making does not take place in a vacuum or in isolation from reality. Currently, systematic a priori and a posteriori modeling methods based on fuzzy propositions provide conditions for embedding contextual constraints into mathematical models, yet manual construction of such models remains challenging. To address this, this study proposes an automatic modeling method based on large language model (LLM), designs a dedicated prompt template to embed the context constraints, and realizes the output of complete code from natural language input, and meanwhile extends the a priori modeling method to the constrained multiobjective optimization framework to construct a Bi-objective SVRP centered on both customer satisfaction and total cost based on the original SVRP. Experiments are conducted under the sustainability and fairness contexts of decision-makers, drivers, and customers, with 10 generation tests performed on four different LLMs, achieving a maximum solvability rate of 0.9 for a single instance; after transferring the optimal results to four data instances, most results still maintain solvability, with true valu...