{"ID":2875282,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.10509","arxiv_id":"2509.10509","title":"The Anti-Ouroboros Effect: Emergent Resilience in Large Language Models from Recursive Selective Feedback","abstract":"The stability of recursively trained large language models (LLMs) is a foundational problem for AI safety. Prevailing theory predicts model collapse, a progressive degradation when models are trained on their own output. We challenge this narrative by introducing a selective feedback mechanism. Contrary to expectation, instead of merely slowing decay, our experiments provide strong evidence that this pressure reverses it, inducing a statistically significant performance improvement in a Gemma 2B model on a complex summarization task. We name this phenomenon the Anti-Ouroboros Effect. We contrast this with a foundational experiment using a simple classifier, where the theoretical degenerative loop was validated, highlighting the unique dynamics of high-dimensional models. Our findings establish that systemic resilience can be an emergent property of LLMs under simple selection pressure, suggesting a powerful and scalable principle for developing safer and more robust AI systems. Across five generations, a quality-filtered condition improved by 6.6% in ROUGE-L F1 score, whereas an unfiltered control degraded by 3.5% and a random-filter control degraded by 4.2%","short_abstract":"The stability of recursively trained large language models (LLMs) is a foundational problem for AI safety. Prevailing theory predicts model collapse, a progressive degradation when models are trained on their own output. We challenge this narrative by introducing a selective feedback mechanism. Contrary to expectation,...","url_abs":"https://arxiv.org/abs/2509.10509","url_pdf":"https://arxiv.org/pdf/2509.10509v1","authors":"[\"Sai Teja Reddy Adapala\"]","published":"2025-09-02T05:46:28Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}