# From Seed AI to Technological Singularity via Recursively Self-Improving Software

arXiv: https://arxiv.org/abs/1502.06512 · HTML: https://mlsanity.com/paper/1502.06512/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Feb 2015.

## Built on by (most cited first, 9 of 9)

- [Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation](https://mlsanity.com/paper/2310.02304/) (2023)
- [Self-Improvements in Modern Agentic Systems: A Survey](https://mlsanity.com/paper/2607.13104/) (2026)
- [Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap](https://mlsanity.com/paper/2507.00075/) (2025)
- [Generating on Generated: An Approach Towards Self-Evolving Diffusion Models](https://mlsanity.com/paper/2502.09963/) (2025)
- [Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement](https://mlsanity.com/paper/2607.04277/) (2026)
- [Emotion-Gradient Metacognitive RSI (Part I): Theoretical Foundations and Single-Agent Architecture](https://mlsanity.com/paper/2505.07757/) (2025)
- [From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Design](https://mlsanity.com/paper/2606.09663/) (2026)
- [Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement](https://mlsanity.com/paper/2609.13406/) (2026)
- [ReSI: Recursive Safety Improvement toward Resistant and Resilient AI](https://mlsanity.com/paper/2610.12233/) (2026)

## Abstract (arXiv)

Software capable of improving itself has been a dream of computer scientists since the inception of the field. In this work we provide definitions for Recursively Self-Improving software, survey different types of self-improving software, review the relevant literature, analyze limits on computation restricting recursive self-improvement and introduce RSI Convergence Theory which aims to predict general behavior of RSI systems. Finally, we address security implications from self-improving intelligent software.