Research

When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs

Single source1 source14 Oct 2026

arXiv:2606.28438v2 Announce Type: replace-cross Abstract: Recursive self-training can degrade neural generative models when generated data is reused without fresh human data or external quality control.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2606.28438

← Back to all developments · Signals are a development reported by more than one source. See the methodology.