# On the Parallels Between Evolutionary Theory and the State of AI

arXiv: https://arxiv.org/abs/2505.23774 · HTML: https://mlsanity.com/paper/2505.23774/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 188 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 27 of 27)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [Deep Reinforcement Learning: An Overview](https://mlsanity.com/paper/1701.07274/) (2017)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [Modular Multitask Reinforcement Learning with Policy Sketches](https://mlsanity.com/paper/1611.01796/) (2016)
- [Multi-Task Reinforcement Learning with Soft Modularization](https://mlsanity.com/paper/2003.13661/) (2020)
- [Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer](https://mlsanity.com/paper/1609.07088/) (2016)
- [Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization](https://mlsanity.com/paper/1802.01569/) (2018)
- [On the Power of Over-parametrization in Neural Networks with Quadratic Activation](https://mlsanity.com/paper/1803.01206/) (2018)
- [Rethinking Experience Replay: a Bag of Tricks for Continual Learning](https://mlsanity.com/paper/2010.05595/) (2020)
- [AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence](https://mlsanity.com/paper/1905.10985/) (2019)
- [Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey](https://mlsanity.com/paper/2012.09830/) (2020)
- [CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning](https://mlsanity.com/paper/1810.06284/) (2018)
- [Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems](https://mlsanity.com/paper/2006.16225/) (2020)
- [Sub-policy Adaptation for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1906.05862/) (2019)
- [Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex](https://mlsanity.com/paper/1511.00083/) (2015)
- [Neuro-Symbolic AI in 2024: A Systematic Review](https://mlsanity.com/paper/2501.05435/) (2025)
- [Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives](https://mlsanity.com/paper/1906.10667/) (2019)
- [Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AI](https://mlsanity.com/paper/2401.01040/) (2024)
- [Efficient, Safe, and Probably Approximately Complete Learning of Action Models](https://mlsanity.com/paper/1705.08961/) (2017)
- [Learning to Compose Skills](https://mlsanity.com/paper/1711.11289/) (2017)
- [The evolutionary origins of hierarchy](https://mlsanity.com/paper/1505.06353/) (2015)
- [FocusLearn: Fully-Interpretable, High-Performance Modular Neural Networks for Time Series](https://mlsanity.com/paper/2311.16834/) (2023)
- [Directed Structural Adaptation to Overcome Statistical Conflicts and Enable Continual Learning](https://mlsanity.com/paper/2412.04190/) (2024)
- [Evolved Developmental Artificial Neural Networks for Multitasking with Advanced Activity Dependence](https://mlsanity.com/paper/2407.10359/) (2024)
- [Agential AI for Integrated Continual Learning, Deliberative Behavior, and Comprehensible Models](https://mlsanity.com/paper/2501.16922/) (2025)

## Built on by (most cited first, 1 of 1)

- [Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare](https://mlsanity.com/paper/2509.07961/) (2025)

## Abstract (arXiv)

This article critically examines the foundational principles of contemporary AI methods, exploring the limitations that hinder its potential. We draw parallels between the modern AI landscape and the 20th-century Modern Synthesis in evolutionary biology, and highlight how advancements in evolutionary theory that augmented the Modern Synthesis, particularly those of Evolutionary Developmental Biology, offer insights that can inform a new design paradigm for AI. By synthesizing findings across AI and evolutionary theory, we propose a pathway to overcome existing limitations, enabling AI to achieve its aspirational goals.