mlsanityData to 14 Oct 2026

On the Parallels Between Evolutionary Theory and the State of AI

arXiv 2505.23774 ↗First posted 13 May 2025q-bio.NC cs.LG cs.NEcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper 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

27 of 188 references.

References · 27

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
  3. 2021Intriguing Properties of Vision Transformerscited by 446
  4. 2017Deep Reinforcement Learning: An Overviewcited by 333
  5. 2018Deep Learning: A Critical Appraisalcited by 217
  6. 2016Modular Multitask Reinforcement Learning with Policy Sketchescited by 203
  7. 2020Multi-Task Reinforcement Learning with Soft Modularizationcited by 143
  8. 2016Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfercited by 127
  9. 2018Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilizationcited by 104
  10. 2018On the Power of Over-parametrization in Neural Networks with Quadratic Activationcited by 102
  11. 2020Rethinking Experience Replay: a Bag of Tricks for Continual Learningcited by 94
  12. 2019AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligencecited by 86
15 more
  1. 2020Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Surveycited by 85
  2. 2018CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learningcited by 79
  3. 2020Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systemscited by 48
  4. 2019Sub-policy Adaptation for Hierarchical Reinforcement Learningcited by 47
  5. 2015Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortexcited by 45
  6. 2025Neuro-Symbolic AI in 2024: A Systematic Reviewcited by 38
  7. 2019Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitivescited by 30
  8. 2024Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AIcited by 24
  9. 2017Efficient, Safe, and Probably Approximately Complete Learning of Action Modelscited by 16
  10. 2017Learning to Compose Skillscited by 15
  11. 2015The evolutionary origins of hierarchycited by 9
  12. 2023FocusLearn: Fully-Interpretable, High-Performance Modular Neural Networks for Time Seriescited by 5
  13. 2024Directed Structural Adaptation to Overcome Statistical Conflicts and Enable Continual Learningcited by 4
  14. 2024Evolved Developmental Artificial Neural Networks for Multitasking with Advanced Activity Dependencecited by 2
  15. 2025Agential AI for Integrated Continual Learning, Deliberative Behavior, and Comprehensible Modelscited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfarecited by 7