Metraipolis › archive › dc_ff4904038252
The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations — arXiv:2609.18560
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18560
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T15:04:47.156Z
- SHA-256 of the archived text
05815c655b87e0224af08269b0bda837af7509c9ea887bb034e537934f792c85- Stable URL of this page
https://metraipolis.com/documento/dc_ff4904038252
How to cite
The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations — arXiv:2609.18560 — arXiv (en), https://arxiv.org/abs/2609.18560 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff4904038252 (Metraipolis archive dc_ff4904038252, sha256 05815c655b87e0224af08269b0bda837af7509c9ea887bb034e537934f792c85)
BibTeX
@misc{dcff4904038252,
title = {The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations — arXiv:2609.18560},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18560},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff4904038252; sha256 05815c655b87e0224af08269b0bda837af7509c9ea887bb034e537934f792c85},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18560. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Some aspects of AI development resemble a population process in which models are specialised, retrained on the output of peers, or combined by averaging weights. These practices lead to generations of models, in the biological sense studied by population genetics. Here, I develop this parallelism and interpret multigenerational model populations in terms of sexual and asexual reproduction, formally recombining the two fields. I test these analogies in an exact inheritance model, in trained networks (recurrent, feedforward and variational autoencoder generators) and in large language models, and show that they hold generally, with some measurable architecture-specific biases. Training recursively on model output is known to lead to model collapse, a process previously described as akin to genetic drift; I develop all that follows. A minimal model of a learner retrained on its parent's output reproduces the Wright-Fisher process exactly; verified real data added to each generation play the role of immigration, with the surprising finding that the absolute number of real data samples matters, not their share, exactly as in population genetics. Training a child on the average of its parents' outputs cancels the benefit of having several parents, matching blending inheritance (and reviving Jenkin's objection to Darwin), whereas combining parents so that each keeps its strongest contribution preserves it; merged language-model specialists exceeded every parent across seeds (the Fisher-Muller effect); and lineages become reproductively isolated, losing the ability to merge at all, when they have learned conflicting conventions and not when they have merely drifted apart. As AI societies become societies in time as well as in space, a mathematical framework for their inheritance acquires predictive power. Remarkably, that framework can be adapted almost wholesale from biology. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Neural and Evolutionary Computing (cs.NE); Populations and Evolution (q-bio.PE). Pagina del lavoro: https://arxiv.org/abs/2609.18560 — 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 2026-10-15T14:08:19.132Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).