When Does Model Collapse Occur in Structured Interactive Learning?

ArXi:2605.20151v1 Announce Type: new The proliferation of generative artificial intelligence has given rise to an interactive learning environment, where model parameters are continuously updated using not only data generated by natural processes, but also synthetic outputs produced by other models. This paradigm Prior work on model collapse primarily focuses on a single model trained on its own output, failing to capture model performance in multi-model interactive settings.