Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms
This work addresses the challenge of making combinatorial optimization more accessible to non-experts, though it is incremental in applying LLMs to an existing task.
The paper tackles the problem of improving optimization algorithms without requiring specialized expertise by using Large Language Models (LLMs) to generate variants of existing algorithms. The results show that LLM-generated variants often improve solution quality, reduce computational time, and simplify code complexity for 10 baseline algorithms on the Travelling Salesman Problem.
Large Language Models (LLMs) have shown notable potential in code generation for optimization algorithms, unlocking exciting new opportunities. This paper examines how LLMs, rather than creating algorithms from scratch, can improve existing ones without the need for specialized expertise. To explore this potential, we selected 10 baseline optimization algorithms from various domains (metaheuristics, reinforcement learning, deterministic, and exact methods) to solve the classic Travelling Salesman Problem. The results show that our simple methodology often results in LLM-generated algorithm variants that improve over the baseline algorithms in terms of solution quality, reduction in computational time, and simplification of code complexity, all without requiring specialized optimization knowledge or advanced algorithmic implementation skills.