Agentic Neural Architecture Search
Quick Answer
AgentNAS introduces a novel approach to neural architecture search by utilizing large language models to generate high-quality seed architectures.
Quick Take
AgentNAS introduces a novel approach to neural architecture search by utilizing large language models to generate high-quality seed architectures. This method establishes a new state of the art on 11 out of 17 tasks across various modalities, outperforming traditional expert designs and demonstrating the complementary benefits of LLM-driven design and conventional NAS.
Key Points
- AgentNAS combines LLM-generated seed architectures with conventional NAS for efficient search.
- Achieved state-of-the-art performance on 11 out of 17 diverse tasks.
- Demonstrated that LLM-generated seeds outperform existing baselines on most tasks.
- The approach is robust across three different LLMs with varying capabilities.
- Code for AgentNAS is publicly available for further research.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Neural architecture search (NAS) methods have grown increasingly efficient, yet they remain bounded by manually engineered search spaces that require substantial domain expertise and must be rebuilt for every new task. Large language models (LLMs) can generate architectures in an open-ended space, but how to optimally divide the labor between LLM-driven design and NAS-driven search remains unexplored. We propose a mechanism that bridges these two paradigms: an LLM produces a high-quality seed architecture, then decomposes it into a "slotted architecture", a scaffold with named, interchangeable module slots that automatically defines a bounded, task-specific search space for conventional NAS to explore, without manual engineering. We instantiate this mechanism in AgentNAS, a modular three-phase pipeline in which each component's contribution can be measured independently. On 17 tasks spanning classification, dense regression, segmentation, and multi-label tagging across diverse modalities (NAS-Bench-360 and Unseen NAS), AgentNAS establishes a new state of the art on 11 tasks, outperforming published baselines including task-specific expert designs. Ablation studies show that the two search mechanisms are broadly complementary: the LLM-generated seed already surpasses published baselines on the majority of tasks, and NAS delivers additional gains in most cases through combinatorial recombination across slots, a mode of search that independent LLM samples cannot replicate. These patterns hold across three LLMs of different capability levels, confirming that the division of labor is robust. Our code is available at this https URL.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.07984 [cs.AI] |
| (or arXiv:2607.07984v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.07984 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Seokhoon Jeong [view email]
[v1]
Wed, 8 Jul 2026 23:20:30 UTC (1,659 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Adversarial Social Epistemology for Assemblies of Humans and Large Language Models
The paper introduces Adversarial Social Epistemology (ASE) to analyze how agents manipulate trust in public communications, highlighting mechanisms that undermine the reliability of testimony and inference. It critiques existing frameworks like epistemic bubbles and misinformation diffusion, proposing a new language for understanding trust breaches and auditing inferential chains in densely interactive environments involving humans and large language models.