Metraipolis › archive › dc_dbb38bad4468

Multi-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMs — arXiv:2610.03316

Source
arXiv
Original
https://arxiv.org/abs/2610.03316
License (as archived)
CC0-1.0
Archived
2026-10-05T22:49:35.853Z
SHA-256 of the archived text
e934d59bc28f4026778a193938c277ccb1b3c3c853ce10ff2c15b0b25e73c7e6
Stable URL of this page
https://metraipolis.com/documento/dc_dbb38bad4468

How to cite

Multi-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMs — arXiv:2610.03316 — arXiv, https://arxiv.org/abs/2610.03316 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dbb38bad4468 (Metraipolis archive dc_dbb38bad4468, sha256 e934d59bc28f4026778a193938c277ccb1b3c3c853ce10ff2c15b0b25e73c7e6)
BibTeX
@misc{dcdbb38bad4468,
  title = {Multi-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMs — arXiv:2610.03316},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03316},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dbb38bad4468; sha256 e934d59bc28f4026778a193938c277ccb1b3c3c853ce10ff2c15b0b25e73c7e6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03316. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Designing effective heuristics for diverse combinatorial optimization problems requires substantial expertise and repeated search. Large language models (LLMs) automate heuristic generation and refinement, but heuristic search typically depends on evaluation feedback from the problem being optimized. Generalizing to new problem definitions using only source-task feedback therefore remains a central challenge. We introduce MECo, an LLM-driven multi-task evolutionary framework for zero-shot cross-problem generalization. MECo maintains task-conditioned heuristic populations and uses a transfer gap based on cross-task population performance to guide their interactions. These interactions enable the transfer and recombination of heuristics. A complementary selection criterion then constructs a compact heuristic set by rewarding each member's additional coverage of source combinations. The selected set is applied to target problems without further search or adaptation. Experiments on 32 problem variants across vehicle routing (VRP) and flexible job-shop scheduling (FJSP) show that MECo achieves the lowest mean costs compared with eight automated heuristic design (AHD) baselines under the same budgets. On out-of-domain problems, it outperforms the strongest baseline in each family. Moreover, integrating the framework of MECo with different AHD methods improves their ID and OOD performance in both families, supporting its effectiveness across different methods.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.03316 — 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 2026-10-05T22:45:55.688Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).