Metraipolis › archive › dc_49fa6c668048

Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zero — arXiv:2609.35328

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35328
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:43.422Z
SHA-256 of the archived text
b1b69a2fa4f34c0572bb51d1808a1187cad5b3c709e82cc6681b79676cb47509
Stable URL of this page
https://metraipolis.com/documento/dc_49fa6c668048

How to cite

Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zero — arXiv:2609.35328 — arXiv (en), https://arxiv.org/abs/2609.35328 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49fa6c668048 (Metraipolis archive dc_49fa6c668048, sha256 b1b69a2fa4f34c0572bb51d1808a1187cad5b3c709e82cc6681b79676cb47509)
BibTeX
@misc{dc49fa6c668048,
  title = {Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zero — arXiv:2609.35328},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35328},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49fa6c668048; sha256 b1b69a2fa4f34c0572bb51d1808a1187cad5b3c709e82cc6681b79676cb47509},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35328. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Meta-Black-Box Optimization (MetaBBO) is one of the highlights in the recent AI for Optimization trend. This paradigm's bi-level workflow leverages the learnable algorithm design policy at meta level to ensure the performance and generalization improvement on the low-level optimization task. While MetaBBO helps advance the performance lower bound of the resulted optimization system, it is currently handcrafted and customized case by case to adapt different optimization problems, which inevitably introduces inherent subjectivity and hence restricts the performance upper bound and usability in practice. In this paper, we address this issue by regarding MetaBBO's design loop as coding task, where we could introduce openendedness into MetaBBO with recursive self-improvement capability of advanced coding agents. Specifically, we propose a dual-agent framework: i) a task agent continuously refines the codebase of a target MetaBBO approach through code evolution; ii) a hyper agent progressively modifies the task agent and itself to provide open-ended design behavior; iii) the evolved MetaBBO codebase is evaluated and all in-execution information is fed back to the agents for recursive self-referential improvement. As a result, given a naive MetaBBO template, our framework automates a design evolution and finds novel variants superior to up-to-date human-made MetaBBO baselines. Surprisingly, the experimental results also demonstrate that our framework supports fast adaption across different optimization domains. Solid interpretation analysis further reveals interesting design principles emerge in such open-ended process. This work serves as the first exploration on automating design of complex learning-assisted optimization algorithms.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.35328 — 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 2026-10-07T20:29:01.836Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).