Metraipolis › archive › dc_1567ecdff3b5

MuEvo: LLM-Driven Evolution of Multi-Heuristic Ensemble — arXiv:2608.03636

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03636
License (as archived)
CC0-1.0
Archived
2026-10-31T12:19:30.686Z
SHA-256 of the archived text
7696449efc041aab3fc4b00c0e14e3607918fc4e59c692aa0ec8e899bdad2081
Stable URL of this page
https://metraipolis.com/documento/dc_1567ecdff3b5

How to cite

MuEvo: LLM-Driven Evolution of Multi-Heuristic Ensemble — arXiv:2608.03636 — arXiv (en), https://arxiv.org/abs/2608.03636 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1567ecdff3b5 (Metraipolis archive dc_1567ecdff3b5, sha256 7696449efc041aab3fc4b00c0e14e3607918fc4e59c692aa0ec8e899bdad2081)
BibTeX
@misc{dc1567ecdff3b5,
  title = {MuEvo: LLM-Driven Evolution of Multi-Heuristic Ensemble — arXiv:2608.03636},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03636},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1567ecdff3b5; sha256 7696449efc041aab3fc4b00c0e14e3607918fc4e59c692aa0ec8e899bdad2081},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03636. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03636 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:05:53.069Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).