Metraipolis › archive › dc_8ee86b7a265e

LLM-Guided Program Evolution for Circle Packing: Breaking 10 Packomania Records for $28 — arXiv:2609.05093

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05093
License (as archived)
CC0-1.0
Archived
2026-10-16T22:21:16.521Z
SHA-256 of the archived text
9a128317da29a5bf26636f9459872fbdaf2b829d6b1c5800483a6603d476a025
Stable URL of this page
https://metraipolis.com/documento/dc_8ee86b7a265e

How to cite

LLM-Guided Program Evolution for Circle Packing: Breaking 10 Packomania Records for $28 — arXiv:2609.05093 — arXiv (en), https://arxiv.org/abs/2609.05093 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8ee86b7a265e (Metraipolis archive dc_8ee86b7a265e, sha256 9a128317da29a5bf26636f9459872fbdaf2b829d6b1c5800483a6603d476a025)
BibTeX
@misc{dc8ee86b7a265e,
  title = {LLM-Guided Program Evolution for Circle Packing: Breaking 10 Packomania Records for $28 — arXiv:2609.05093},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05093},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8ee86b7a265e; sha256 9a128317da29a5bf26636f9459872fbdaf2b829d6b1c5800483a6603d476a025},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05093. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present Discovery Loop, a lightweight system that uses a large language model (LLM) to iteratively evolve optimization algorithms. Starting from a simple seed solver, the LLM proposes algorithmic improvements guided by a scoreboard of results and a history of prior ideas. Each candidate is evaluated against an independent verifier; improvements are kept and failures discarded. Applied to the Packomania circle-packing benchmark (csqv: maximize the sum of radii of N variable-radius circles in the unit square), the system improved the best known solutions for 10 values of N in the range 101-114, with gains of 2.4%-5.4% over prior records, all within 15 iterations and at a total LLM cost of $27.72. These results have been independently accepted by Packomania. We describe the method, analyze cost-efficiency dynamics including an adaptive plateau-detection mechanism, and discuss implications for democratizing automated scientific discovery.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.05093 — 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 2026-10-16T22:18:11.433Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).