Over the last few decades, there has been a considerable effort to make decision support more accessible for small and medium enterprises by reducing the cost of design, development and maintenance of automated decision support systems. However, due to the diversity of the underlying combinatorial optimisation problems, reusability of such systems has been limited; in most cases, expensive expertise has been necessary to implement bespoke software components. We investigate the possibility of fully automated generation of combinatorial optimisation systems by utilising the large language models (LLMs). An LLM will be responsible for interpreting the problem description provided by the user in a natural language and designing and implementing problem-specific software components. We discuss the principles of fully automated LLM-based generation of optimisation systems, and evaluate several proof-of-concept generators, comparing their performance on four optimisation problems.
翻译:暂无翻译