Algorithm Evolution Using Large Language Model
This work addresses the challenge of algorithm design for optimization problems, potentially reducing expert effort, but it is incremental as it builds on existing evolutionary and LLM-based methods.
The paper tackles the problem of designing optimization algorithms by proposing AEL, which uses a large language model in an evolutionary framework to automatically generate algorithms, reducing human effort and domain knowledge requirements; it demonstrates that AEL-generated algorithms outperform hand-crafted and LLM-generated heuristics for the traveling salesman problem and show excellent scalability across problem sizes.
Optimization can be found in many real-life applications. Designing an effective algorithm for a specific optimization problem typically requires a tedious amount of effort from human experts with domain knowledge and algorithm design skills. In this paper, we propose a novel approach called Algorithm Evolution using Large Language Model (AEL). It utilizes a large language model (LLM) to automatically generate optimization algorithms via an evolutionary framework. AEL does algorithm-level evolution without model training. Human effort and requirements for domain knowledge can be significantly reduced. We take constructive methods for the salesman traveling problem as a test example, we show that the constructive algorithm obtained by AEL outperforms simple hand-crafted and LLM-generated heuristics. Compared with other domain deep learning model-based algorithms, these methods exhibit excellent scalability across different problem sizes. AEL is also very different from previous attempts that utilize LLMs as search operators in algorithms.