# Eliminating Meta Optimization Through Self-Referential Meta Learning

arXiv: https://arxiv.org/abs/2212.14392 · HTML: https://mlsanity.com/paper/2212.14392/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 29 Dec 2022.

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Meta-Learning with Warped Gradient Descent](https://mlsanity.com/paper/1909.00025/) (2019)
- [Differentiable plasticity: training plastic neural networks with backpropagation](https://mlsanity.com/paper/1804.02464/) (2018)
- [Improving Generalization in Meta Reinforcement Learning using Learned Objectives](https://mlsanity.com/paper/1910.04098/) (2019)
- [Learning Associative Inference Using Fast Weight Memory](https://mlsanity.com/paper/2011.07831/) (2020)
- [Meta Learning Backpropagation And Improving It](https://mlsanity.com/paper/2012.14905/) (2020)
- [A Modern Self-Referential Weight Matrix That Learns to Modify Itself](https://mlsanity.com/paper/2202.05780/) (2022)
- [Introducing Symmetries to Black Box Meta Reinforcement Learning](https://mlsanity.com/paper/2109.10781/) (2021)
- [BADGER: Learning to (Learn [Learning Algorithms] through Multi-Agent Communication)](https://mlsanity.com/paper/1912.01513/) (2019)

## Built on by (most cited first, 14 of 14)

- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Language Agents as Optimizable Graphs](https://mlsanity.com/paper/2402.16823/) (2024)
- [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)
- [Brain-inspired learning in artificial neural networks: a review](https://mlsanity.com/paper/2305.11252/) (2023)
- [The Red Queen G"odel Machine: Co-Evolving Agents and Their Evaluators](https://mlsanity.com/paper/2606.26294/) (2026)
- [Self-Improvements in Modern Agentic Systems: A Survey](https://mlsanity.com/paper/2607.13104/) (2026)
- [SymbolicAI: A framework for logic-based approaches combining generative models and solvers](https://mlsanity.com/paper/2402.00854/) (2024)
- [Deceptive Alignment Monitoring](https://mlsanity.com/paper/2307.10569/) (2023)
- [Boundless Socratic Learning with Language Games](https://mlsanity.com/paper/2411.16905/) (2024)
- [Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization](https://mlsanity.com/paper/2604.23472/) (2026)
- [Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap](https://mlsanity.com/paper/2507.00075/) (2025)
- [Arbitrary Order Meta-Learning with Simple Population-Based Evolution](https://mlsanity.com/paper/2303.09478/) (2023)
- [Meta-Agent: From Task Descriptions to Verified Multi-Agent Systems](https://mlsanity.com/paper/2605.25233/) (2026)
- [MMLA-RSI: Recursive Self-Improvement through RTT and RTMA](https://mlsanity.com/paper/2610.20294/) (2026)

## Abstract (arXiv)

Meta Learning automates the search for learning algorithms. At the same time, it creates a dependency on human engineering on the meta-level, where meta learning algorithms need to be designed. In this paper, we investigate self-referential meta learning systems that modify themselves without the need for explicit meta optimization. We discuss the relationship of such systems to in-context and memory-based meta learning and show that self-referential neural networks require functionality to be reused in the form of parameter sharing. Finally, we propose fitness monotonic execution (FME), a simple approach to avoid explicit meta optimization. A neural network self-modifies to solve bandit and classic control tasks, improves its self-modifications, and learns how to learn, purely by assigning more computational resources to better performing solutions.