.png){kind=icon}
.png){kind=icon}
Return
LLMENAS: Evolutionary Neural Architecture Search via Large Language Model Guidance
.png){kind=icon}
PRE
AI
Y
Z
L
T
H
DOI：10.1109/tevc.2026.3670336.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Differentiable neural architecture search (NAS) and traditional evolutionary approaches frequently struggle with premature convergence to local optima. To overcome this limitation, we propose LLMENAS, a hierarchical framework that introduces trajectory-aware fitness design as the upper-level optimizer. By analyzing the convergence state of historical optimization trajectories, the large language model (LLM) acts as a fitness designer to dynamically design fitness functions. This mechanism enables the search to navigate complex landscapes and escape local optima. Furthermore, we introduce a closed-loop self-improving mechanism, enabling the LLM to iteratively enhance its design strategies through self-reflection and self-refinement based on feedback. Extensive experiments show that LLMENAS achieves competitive results, with top-1 accuracies of 97.58% on CIFAR-10, 83.52% on CIFAR-100, and 75.6% on ImageNet-1k. Furthermore, it is achieved with remarkable efficiency, costing only 0.15 GPU days on the CIFAR 10 datasets and 2 GPU days on ImageNet. The source code is publicly available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/LLMENAS/LLMENAS</uri>
Keywords:
Evolutionary strategy
image classification
large language model (LLM)
neural architecture search (NAS)
Journal
IF:
12
Papers:
1.8K
Citations:
2.4W
Organization
Cited Papers