From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution
This work addresses the problem of automated algorithm design for researchers and practitioners by providing a more flexible and globally optimized approach, though it appears incremental as it builds on existing LLM-based methods.
The paper tackles the limitation of current LLM-based algorithm generation methods that rely on predefined templates and local optimization by introducing an end-to-end framework that uses LLMs to convert natural language requirements into code and employs a two-dimensional co-evolution strategy to optimize both functional and structural aspects. The method outperforms traditional approaches in performance and innovation, generating novel algorithms that surpass human-designed ones.
Large language models (LLMs) have greatly accelerated the automation of algorithm generation and optimization. However, current methods such as EoH and FunSearch mainly rely on predefined templates and expert-specified functions that focus solely on the local evolution of key functionalities. Consequently, they fail to fully leverage the synergistic benefits of the overall architecture and the potential of global optimization. In this paper, we introduce an end-to-end algorithm generation and optimization framework based on LLMs. Our approach utilizes the deep semantic understanding of LLMs to convert natural language requirements or human-authored papers into code solutions, and employs a two-dimensional co-evolution strategy to optimize both functional and structural aspects. This closed-loop process spans problem analysis, code generation, and global optimization, automatically identifying key algorithm modules for multi-level joint optimization and continually enhancing performance and design innovation. Extensive experiments demonstrate that our method outperforms traditional local optimization approaches in both performance and innovation, while also exhibiting strong adaptability to unknown environments and breakthrough potential in structural design. By building on human research, our framework generates and optimizes novel algorithms that surpass those designed by human experts, broadening the applicability of LLMs for algorithm design and providing a novel solution pathway for automated algorithm development.