The Oligarch Barely Steers Model Collapse in Multi-Model Ecosystems

<p>Here is a slightly uncomfortable thought experiment. Photocopy a photograph. Now photocopy the photocopy, and the copy of that, and keep going. Within a dozen generations the

arXiv:2605.04454v1 Announce Type: new Abstract: Alignment evaluation in machine learning has largely become evaluation of models. Influential benchmarks score model outputs under

arXiv:2606.13732v1 Announce Type: new Abstract: The proliferation of recursive training on synthetic data can alleviate data scarcity but risks model collapse, where repeated

arXiv:2604.08554v1 Announce Type: cross Abstract: The public text record -- the material from which both people and AI systems now learn -- is increasingly shaped by its own

arXiv:2604.22748v1 Announce Type: new Abstract: As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment

arXiv:2605.00435v1 Announce Type: cross Abstract: Mode collapse is a persistent challenge in generative modeling and appears in autoregressive text generation as behaviors ranging

arXiv:2608.11392v2 Announce Type: cross Abstract: Long-running agents periodically compact their context, replacing the transcript with a model-generated summary. Recent work

<blockquote> <p><em>Originally published at <a href="https://adiyogiarts.com/blog/understanding-generative-model-collapse-in-llms" rel="noopener