# Bounded Recursive Self-Improvement

arXiv: https://arxiv.org/abs/1312.6764 · HTML: https://mlsanity.com/paper/1312.6764/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2013.

## Built on by (most cited first, 10 of 10)

- [Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation](https://mlsanity.com/paper/2310.02304/) (2023)
- [Huxley-G"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine](https://mlsanity.com/paper/2510.21614/) (2025)
- [Self-Improvements in Modern Agentic Systems: A Survey](https://mlsanity.com/paper/2607.13104/) (2026)
- [Neurosymbolic Systems of Perception & Cognition: The Role of Attention](https://mlsanity.com/paper/2112.01603/) (2021)
- [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)
- [From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Design](https://mlsanity.com/paper/2606.09663/) (2026)
- [Project Auto-World: Towards Automated Benchmarking of Neural Relational Reasoners](https://mlsanity.com/paper/2606.24965/) (2026)
- [Dalek: A Constructive Agent Machine](https://mlsanity.com/paper/2609.03546/) (2026)
- [Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement](https://mlsanity.com/paper/2609.13406/) (2026)

## Abstract (arXiv)

We have designed a machine that becomes increasingly better at behaving in underspecified circumstances, in a goal-directed way, on the job, by modeling itself and its environment as experience accumulates. Based on principles of autocatalysis, endogeny, and reflectivity, the work provides an architectural blueprint for constructing systems with high levels of operational autonomy in underspecified circumstances, starting from a small seed. Through value-driven dynamic priority scheduling controlling the parallel execution of a vast number of reasoning threads, the system achieves recursive self-improvement after it leaves the lab, within the boundaries imposed by its designers. A prototype system has been implemented and demonstrated to learn a complex real-world task, real-time multimodal dialogue with humans, by on-line observation. Our work presents solutions to several challenges that must be solved for achieving artificial general intelligence.