Semantics-Aware Bilevel Co-Evolution: Towards Automated Multicomponent Algorithm Design

2026-06-29

AI Summary

Existing LLM-assisted evolutionary search methods struggle to balance component reuse and configuration exploration when automatically designing complex multi-component algorithms, and they lack explicit modeling of algorithmic semantics, leading to inefficient search. This work proposes STABLE, a novel semantic-aware bi-level co-evolutionary framework that represents algorithms through a hierarchical modular structure: optimizing component configurations at the high level and refining functional implementations at the low level. A multi-dimensional semantic model guides the LLM in cross-level component generation and evaluation. Experimental results demonstrate that STABLE significantly outperforms both handcrafted baselines and state-of-the-art automated methods across multiple complex algorithm design tasks, confirming its effectiveness and generalization capability.

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.

Problem

• automated algorithm design
• multicomponent algorithms
• algorithm semantics
• evolutionary search
• design space exploration

Innovation

• Semantics-Aware Evolution
• Bilevel Co-Evolution
• Multicomponent Algorithm Design
• LLM-assisted Search
• Structured Algorithm Formulation