论文研究
arxiv.org ·
人工智能有性繁殖的演化：多代模型种群的群体遗传学框架
该 arXiv 预印本将多代模型种群类比为群体遗传学中的有性与无性繁殖，并在精确继承模型、已训练网络（循环、前馈、VAE 生成器）及大语言模型上检验该类比。作者称：在父代输出上递归重训的最小学习器精确复现 Wright-Fisher 过程；每代加入的真实数据相当于移民，且起作用的是真实样本的绝对数量而非占比；对父代输出取平均会抵消多父代收益（对应融合遗传），而保留各父代最强贡献的组合可保留收益，合并后的语言模型专家在多个随机种子上超过任一父代（Fisher-Muller 效应）；当谱系学到冲突约定而非仅漂移分化时会出现生殖隔离。作者认为该框架可从生物学几乎整体移植，对 AI 社会的继承具有预测力。
AI推荐理由 arXiv 预印本，作者为 Giorgio F. Gilestro，摘要给出明确的理论框架与实验对象（递归、前馈、VAE 生成器及大语言模型），并报告了若干可检验结论：在父代输出上重训的最小模型精确复现 Wright-Fisher 过程；每代加入的真实数据起“移民”作用，且起作用的是真实样本的绝对数量而非占比；对父代输出取平均会抵消多父代收益（类似融合遗传），而保留各父代最强贡献的组合可保留收益，合并后的语言模型专家在多个随机种子上超过任一父代（Fisher-Muller 效应）；当谱系学到冲突约定而非仅漂移分化时会出现生殖隔离。这些是具体的新信息，对模型合并、多代训练与模型崩溃研究有参考价值。局限：仅为预印本，未经同行评审，摘要未给出数据集、规模与统计细节，结论需进一步验证；标题中的“有性繁殖”是类比框架，不应读作 AI 已具备生物意义上的繁殖。
72
正文
Computer Science > Machine Learning
arXiv:2609.18560 (cs)
[Submitted on 16 Sep 2026]
Title:The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations
Authors:Giorgio F. Gilestro
View a PDF of the paper titled The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations, by Giorgio F. Gilestro
View PDF
HTML (experimental)
Abstract: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.
Comments:
Subjects:
Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Populations and Evolution (q-bio.PE)
Cite as:
arXiv:2609.18560 [cs.LG]
(or
arXiv:2609.18560v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.18560
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Giorgio F. Gilestro [view email]
[v1]
Wed, 16 Sep 2026 12:20:30 UTC (5,226 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations, by Giorgio F. Gilestro
View PDF
HTML (experimental)
TeX Source
view license
Ancillary-file links:
Ancillary files (details):
figures_explained.pdf
supplementary_information.pdf
Current browse context:
cs.LG
new
|
recent
| 2026-09
Change to browse by:
cs
cs.NE
q-bio
q-bio.PE
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender
(What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)