← Back to all news
arXiv Machine Learning

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

The paper draws a parallel between AI model development and population genetics, treating successive model generations as analogous to sexual and asexual reproduction. It demonstrates that training models on peers’ outputs reproduces classic genetic processes such as the Wright–Fisher model, while combining parents’ weights can either cancel or preserve inherited advantages depending on the method. Experiments across recurrent, feedforward, and language models confirm these analogies and reveal architecture‑specific biases, including the Fisher‑Muller effect and reproductive isolation when lineages learn conflicting conventions.

Related stories

arXiv Computation and Language
Sep 25

What a Cross-Model Fixed-Point Census Can and Cannot Arbitrate About Repetition

The paper investigates neural text degeneration by measuring the fixed‑point structure of short‑window argmax maps across 17 pretrained models, using 96 random two‑token starts without prompts. It finds a stable four‑way classification that varies across model families and scales, with some models funneling to a single endpoint token while others do not, and shows that this behavior is not solely determined by training data or corpus frequency. The study demonstrates that repetition phenomena are not uniformly explained by either training data or network architecture alone, highlighting the complexity of neural text generation dynamics.

By Nicol\'as Vera Z\'u\~niga
llms
More like this →
arXiv AI
Sep 2

Flawed in Nature, Perfect through Evolution

arXiv:2609.00129v1 Announce Type: cross Abstract: The performance of artificial intelligence (AI) and machine learning (ML) models degrades when the problem they were trained on drifts. This is a nea...

By J. M. Diederik Kruijssen (Allora Foundation)
More like this →
arXiv Machine Learning
Sep 11

A Fragility Spectrum for Recursive Language-Model Training

The paper investigates how recursive contamination—retraining language models on their own generated text—affects output diversity across 13 publicly released checkpoints. Using a fixed contamination protocol over five generations, the authors find a wide spread in 4‑gram diversity (0.187 to 0.940), indicating that some models collapse into repetitive fragments while others remain largely unaffected. The study shows that a model’s susceptibility to collapse is an intrinsic property of the checkpoint, not predicted by parameter scale or static indicators, and that simple interventions such as tightening top‑p sampling can significantly slow or halt collapse.

By Yangze Liu, Zhongyi Han
More like this →