Semantics-Aware Bilevel Co-Evolution: Towards Automated Multicomponent Algorithm Design
2026-06-29 • Neural and Evolutionary Computing
Neural and Evolutionary Computing
AI summaryⓘ
The authors address challenges in using large language models (LLMs) to design complex algorithms made of multiple parts. They point out that past methods either change whole algorithms at once or only tweak parts within fixed setups, which limits efficiency. To fix this, they created STABLE, a system that organizes algorithms into neat, modular structures and uses knowledge about how parts fit and work together. STABLE improves design by guiding the search with a semantic understanding of components, helping generate and evaluate better algorithms. Their tests show STABLE outperforms existing automated design methods and human-created baselines.
LLM-assisted evolutionary searchautomated algorithm designmulticomponent algorithmssemantic modelingmodular architecturesbilevel co-evolutiondesign space explorationalgorithm optimizationlarge language modelsevolutionary algorithms
Authors
Zhiyao Zhang, Shenghao Wu, Xingyu Wu, Kay Chen Tan
Abstract
LLM-assisted evolutionary search (LES) has emerged as a promising paradigm for automated algorithm design. However, existing methods usually suffer from two inherent limitations when facing the automated design of real-world complex algorithms that usually consist of multiple components. The first limitation is that they either focus on modifying entire algorithms, making it difficult to reuse high-quality components, or concentrate on component refinement within a limited set of predefined multicomponent configurations. The second limitation is the insufficient explicit modeling and exploitation of algorithm semantics. These limitations severely degrade search efficiency and hinder effective exploration of complex design spaces. Therefore, this paper proposes STABLE (Semantics-Aware Bilevel Co-Evolution), an LES method purpose-built for automated multicomponent algorithm design that introduces structural algorithm formulation and semantics-driven evolution. In STABLE, complex algorithms are organized into hierarchical and modular architectures rooted in domain knowledge, aligning the search space with their intrinsic compositional traits. Based on this structured algorithm formulation, STABLE simultaneously optimizes high-level multicomponent configurations and low-level functional components, enabling coordinated cross-level updates while maintaining suitable granularities for design space exploration. At each level, STABLE establishes a multi-faceted semantic model to assist LLMs in capturing structural correlations, functional compatibilities, and inherent rationalities among algorithm components. This semantic model serves as the core guidance for evolutionary search, enabling principled algorithm generation and algorithm evaluation. Extensive experiments demonstrate that STABLE outperform both human-designed baselines and those from advanced LES methods.