AI RESEARCH
LLM as a Tool, Not an Agent: Code-Mined Tree Transformations for Neural Architecture Search
arXiv CS.LG
•
ArXi:2604.16555v1 Announce Type: new Neural Architecture Search (NAS) aims to automatically discover high-performing deep neural network (DNN) architectures. However, conventional algorithm-driven NAS relies on carefully hand-crafted search spaces to ensure executability, which restricts open-ended exploration. Recent coding-based agentic approaches using large language models (LLMs) reduce manual design, but current LLMs struggle to reliably generate complex, valid architectures, and their proposals are often biased toward a narrow set of patterns observed in their