AgentNAS: LLM-Designed Seed Architectures Boost Neural Architecture Search

Jul 10, 2026

Researchers introduce AgentNAS, a method where a large language model (LLM) generates a seed architecture and decomposes it into a slotted scaffold, defining a task-specific search space for neural architecture search (NAS) without manual engineering. Evaluated on 17 tasks, AgentNAS achieves state-of-the-art results on 11, outperforming published baselines including expert designs. Ablation studies show the LLM-generated seed alone surpasses baselines on most tasks, with NAS providing further complementary improvements.

Why it matters: This work automates the creation of task-specific NAS search spaces by combining LLM-driven design with NAS-driven search, reducing the need for manual engineering.

Full story at: arXiv AI/ML ↗