The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations

2026-09-16

AI Summary

该研究通过将人工智能模型的多代演化与生物学中的有性和无性繁殖类比，利用遗传学框架解释AI模型训练过程中的现象，并验证了这些类比在多种网络结构下的有效性。

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.

Problem

• multigenerational model populations
• sexual and asexual reproduction
• model collapse
• inherited characteristics
• reproductive isolation

Innovation

• multigenerational model populations
• sexual and asexual reproduction
• Wright-Fisher process
• blending inheritance
• Fisher-Muller effect