# Evolutionary-Neural Hybrid Agents for Architecture Search

arXiv: https://arxiv.org/abs/1811.09828 · HTML: https://mlsanity.com/paper/1811.09828/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2018.

## Built on by (most cited first, 11 of 11)

- [How Powerful are Performance Predictors in Neural Architecture Search?](https://mlsanity.com/paper/2104.01177/) (2021)
- [An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems](https://mlsanity.com/paper/2205.12755/) (2022)
- [AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search](https://mlsanity.com/paper/2506.06017/) (2025)
- [muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems](https://mlsanity.com/paper/2205.10937/) (2022)
- [A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems](https://mlsanity.com/paper/2209.07326/) (2022)
- [Task Selection for AutoML System Evaluation](https://mlsanity.com/paper/2208.12754/) (2022)
- [EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning](https://mlsanity.com/paper/2308.09915/) (2023)
- [Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition](https://mlsanity.com/paper/2103.16889/) (2021)
- [Training BatchNorm Only in Neural Architecture Search and Beyond](https://mlsanity.com/paper/2112.00265/) (2021)
- [A Multiagent Framework for the Asynchronous and Collaborative Extension of Multitask ML Systems](https://mlsanity.com/paper/2209.14745/) (2022)
- [Multipath agents for modular multitask ML systems](https://mlsanity.com/paper/2302.02721/) (2023)

## Abstract (arXiv)

Neural Architecture Search has shown potential to automate the design of neural networks. Deep Reinforcement Learning based agents can learn complex architectural patterns, as well as explore a vast and compositional search space. On the other hand, evolutionary algorithms offer higher sample efficiency, which is critical for such a resource intensive application. In order to capture the best of both worlds, we propose a class of Evolutionary-Neural hybrid agents (Evo-NAS). We show that the Evo-NAS agent outperforms both neural and evolutionary agents when applied to architecture search for a suite of text and image classification benchmarks. On a high-complexity architecture search space for image classification, the Evo-NAS agent surpasses the accuracy achieved by commonly used agents with only 1/3 of the search cost.