mlsanityData to 14 Oct 2026

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

arXiv 1502.06512 ↗First posted 23 Feb 2015cs.AIcited by 9

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 3; 2026: 5.

9 papers.

  1. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 148
  2. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  3. 2025Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gapcited by 6
  4. 2025Generating on Generated: An Approach Towards Self-Evolving Diffusion Modelscited by 3
  5. 2026Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvementcited by 2
  6. 2025Emotion-Gradient Metacognitive RSI (Part I): Theoretical Foundations and Single-Agent Architecturecited by 0
  7. 2026From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Designcited by 0
  8. 2026Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvementcited by 0
  9. 2026ReSI: Recursive Safety Improvement toward Resistant and Resilient AIcited by 0