Skip to content
Preprint

MuEvo: LLM-Driven Evolution of Multi-Heuristic Ensemble

Aug 2026 · 0 citations · 48 references
Computer Science

Abstract

Large language model-based automated heuristic design (LLM-AHD) has shown strong potential in discovering effective heuristics for combinatorial optimization problems. However, existing methods primarily optimize a single heuristic, whereas practical optimization frameworks often rely on multiple interacting components. Directly extending single-heuristic methods is challenging because early component selection can overlook components with late potential, while independent evolution ignores inter-component dependencies. We propose MuEvo, an LLM-driven framework for evolving heuristic ensembles under ensemble-level feedback. MuEvo combines Dynamic Component Management, which uses short-budget probing and a reversible lifecycle to revise component priorities throughout the search, with LLM-Driven Co-Evolution, which coordinates component populations through Multi-Ensemble Evaluation, Cross-Component Information Sharing, Relation-Guided Pair Evolution, and Adaptive Budget Allocation. We evaluate MuEvo on selection hyper-heuristics and componentized ant colony optimization across four combinatorial optimization domains. Results show that MuEvo consistently improves human-designed frameworks and outperforms representative multi-component extensions of state-of-the-art LLM-AHD methods, demonstrating its effectiveness across both controller-mediated heuristic pools and functionally differentiated algorithmic components.

View source

Similar papers

Book Open access Jul 2026

QDEvo: A Multi-Objective Quality-Diversity Framework for Automated Heuristic Design

Large Language Models (LLMs) are opening new directions for automated heuristic design (AHD), allowing evolutionary methods to create and enhance heuristics for constrained optimization problems (COPs). However, most existing approaches face the challenge of the exploration-exploitation balance, where the evolution needs to escape convergence to homogeneous populations and discover as large a heuristic landscape as possible. To address this challenge, we introduce Quality-Diversity Evolution (QDEvo), a multi-objective framework that integrates Quality-Diversity optimization with LLM-based AHD. At its core, QDEvo employs a semantic survival selection mechanism that clusters algorithms by functional similarity, then applies local Pareto competition. Evaluation on well-known COPs benchmarks and real-world problems shows that our method consistently outperforms the state-of-the-art baseline in both Hypervolume and Inverted Generational Distance metrics. These results facilitate further exploration of the algorithmic design space, while ensuring competitive solution quality and efficiency.

Nam Do Khanh, Nhat Nguyen Tran Minh, Dat Pham Vu Tuan et al. · 1 citation
2025

Partition to Evolve: Niching-enhanced Evolution with LLMs for Automated Algorithm Discovery

This work proposes a general LES framework that incorporates feature-assisted niche construction within abstract search spaces, enabling the seamless integration of niche-based search strategies from evolutionary computation and introduces PartEvo (Partition to Evolve), an LES method that combines niche collaborative search and advanced prompting strategies to improve algorithm discovery efficiency.

Qinglong Hu, Qingfu Zhang · 10 citations · ⚡3
Book Open access Jul 2026

EvoHIIT: Preference-Based Selection in LLM-Assisted Evolutionary Design of Natural Language Solutions

EvoHIIT, an LLM-assisted evolutionary framework for the design of High-Intensity Interval Training (HIIT) programs, is introduced, and preference-based selection mechanisms are studied to provide empirical insight into human-aligned evolution of natural language solutions.

Johana Chen, Niki van Stein, Robert Cabri et al. · 0 citations
Preprint Jul 2026

LLM-Driven Evolutionary Generation of Multi-Objective Bayesian Optimization Algorithms

LLM-driven evolutionary search can discover algorithm designs that achieve Pareto-efficient trade-offs difficult to reach through manual design, with SMAC hyperparameter optimization integrated into the evolutionary loop.

G. Laskaris, R. Brasher, Niki van Stein et al. · 0 citations
Book Open access Jul 2026

LLM Policy Induction for Heuristic Search Control: A Trace-Driven ALNS Framework

Experimental results demonstrate that the proposed framework consistently outperforms classical ALNS baselines and several competitive metaheuristic methods in terms of solution quality and convergence speed.

T. M. Nguyen · 0 citations
Book Open access Jul 2026

LLM-Driven Configuration of Genetic Algorithms for Constraint-Rich Optimization Problems

A framework that combines large language models (LLMs) for problem understanding with a structured Biased Random-Key Genetic Algorithm (BRKGA) configurator for algorithm realization is presented, allowing users to describe optimization problems in natural language and receive executable GPU-accelerated GA implementations.

Harishjitu Seesandrn, M. Sodhi, Resit Sendag · 0 citations