Metraipolis › archive › dc_da7bf0b73e9e
LLM-Guided Graph Generation for Structure-Based Local Improvement Methods — arXiv:2608.13333
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13333
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:17:38.871Z
- SHA-256 of the archived text
630e325353727f24e1b5dbea7d3ea534b92055ed27a3e1b7b4c929001a0c5cd4- Stable URL of this page
https://metraipolis.com/documento/dc_da7bf0b73e9e
How to cite
LLM-Guided Graph Generation for Structure-Based Local Improvement Methods — arXiv:2608.13333 — arXiv (en), https://arxiv.org/abs/2608.13333 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da7bf0b73e9e (Metraipolis archive dc_da7bf0b73e9e, sha256 630e325353727f24e1b5dbea7d3ea534b92055ed27a3e1b7b4c929001a0c5cd4)
BibTeX
@misc{dcda7bf0b73e9e,
title = {LLM-Guided Graph Generation for Structure-Based Local Improvement Methods — arXiv:2608.13333},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13333},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da7bf0b73e9e; sha256 630e325353727f24e1b5dbea7d3ea534b92055ed27a3e1b7b4c929001a0c5cd4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13333. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large neighborhood search normally selects a random subset of decision variables for iterative optimization. To efficiently solve various problems, researchers tend to design variable selection strategies that take into account structural features across different domains. In this paper, we build an automatic pipeline that is problem-agnostic to all problems in the MiniZinc format. By prompting an LLM with our semantic guidelines, we guide the LLM to produce a graph generator that maps any instance of a problem type to a uniform weighted graph, where nodes represent decision variables and edges represent constraint relationships. These problem-agnostic graphs guide our structure-based local improvement (SLIM) framework for variable selection. Meanwhile, the weighted graph enables all problem instances to share the same generic graph representation, from which the same graph features can be extracted and used for configuration selection. We evaluated our pipeline on instances across 20 MiniZinc competition problems, finding that algorithm selection achieves a 39.6% average problem-weighted win rate against a one-shot Gurobi baseline, more than doubling the best single configuration (19.3%). A post-hoc configuration and a feature ablation indicate a headroom of up to 44.0%, demonstrating that LLM-based semantic generation enables effective automated structure and feature extraction for constraint optimization. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.13333 — 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 2026-10-19T04:13:06.605Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).