Metraipolis › archive › dc_6d88852fa06c

Is manual software optimization a thing of the past? — arXiv:2609.37849

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37849
License (as archived)
CC0-1.0
Archived
2026-10-07T16:27:47.731Z
SHA-256 of the archived text
1d6a6748b79c686daf052d3c30eecb3739ad79cb37e9db1924fc21af437beb4a
Stable URL of this page
https://metraipolis.com/documento/dc_6d88852fa06c

How to cite

Is manual software optimization a thing of the past? — arXiv:2609.37849 — arXiv (en), https://arxiv.org/abs/2609.37849 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6d88852fa06c (Metraipolis archive dc_6d88852fa06c, sha256 1d6a6748b79c686daf052d3c30eecb3739ad79cb37e9db1924fc21af437beb4a)
BibTeX
@misc{dc6d88852fa06c,
  title = {Is manual software optimization a thing of the past? — arXiv:2609.37849},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37849},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6d88852fa06c; sha256 1d6a6748b79c686daf052d3c30eecb3739ad79cb37e9db1924fc21af437beb4a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37849. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scientific software is increasingly required to process larger datasets while maintaining acceptable execution times. Software optimization traditionally requires substantial expertise in programming, algorithms, and numerical methods. Recent advances in large language models (LLMs) offer the possibility of automating much of this process. We investigate whether LLM-based agents can autonomously achieve substantial performance improvements in scientific software, including mature implementations that have already been extensively optimized by human developers. We tasked an LLM-based agent with optimizing software for three computational problems: t-SNE, single-sample gene set enrichment analysis (ssGSEA), and graphlet counting. Humans defined the scope, correctness criteria, and a verification mechanism, after which the agent worked autonomously, in some cases for several hours. Code maintainers reviewed each resulting implementation and verified its correctness. The optimized implementations were faster in all tested configurations, by up to two orders of magnitude over the fastest existing tools. The improvements included low-level code optimizations, mathematical reformulations, and an entirely new algorithm for graphlet counting. Software optimization can increasingly be delegated to autonomous agents, with the human role shifting from implementing optimizations to deciding which software to optimize, defining objectives, providing verification mechanisms, and ensuring the correctness of the final software. For well-scoped, verifiable problems, we argue that manual software optimization may be a thing of the past.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.37849 — 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 2026-10-07T15:54:54.037Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).