When Your Own Output Becomes Your Training Data: Noise-to-Meaning Loops and a Formal RSI Trigger

We present Noise-to-Meaning Recursive Self-Improvement (N2M-RSI), a minimal formal model showing that once an AI agent feeds its own outputs back as inputs and crosses an explicit information-integration threshold, its internal complexity will grow without bound under our assumptions. The framework unifies earlier ideas on self-prompting large language models, Gödelian self-reference, and AutoML, yet remains implementation-agnostic. The model furthermore scales naturally to interacting swarms of agents, hinting at super-linear effects once communication among instances is permitted. For safety reasons, we omit system-specific implementation details and release only a brief, model-agnostic toy prototype in Appendix C.

@article{ando2025_2505.02888,
  title={ When Your Own Output Becomes Your Training Data: Noise-to-Meaning Loops and a Formal RSI Trigger },
  author={ Rintaro Ando },
  journal={arXiv preprint arXiv:2505.02888},
  year={ 2025 }
}