> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/changelog/explore-by-month/april-2026/neural-architecture-search-in-roboflow-train.md).

# Neural Architecture Search in Roboflow Train

Neural Architecture Search (NAS) is now available as a training engine for object detection and instance segmentation projects. Instead of manually tuning hyperparameters and running multiple separate training jobs, NAS automatically evaluates thousands of candidate architectures in a single run. This allows you to find the optimal balance of inference speed and accuracy tailored to your specific dataset and deployment hardware.

Using a unique weight-sharing strategy, NAS explores these configurations simultaneously at a fraction of the traditional compute cost. Once training is complete, you can evaluate the resulting models on a speed-vs-accuracy graph to deploy the version that best fits your performance requirements, often achieving better latency and accuracy than standard fine-tuning.

[Read the announcement post](https://blog.roboflow.com/train-with-neural-architecture-search/)

[See documentation](https://docs.roboflow.com/train/neural-architecture-search)

[Watch the walkthrough video](https://youtu.be/ZtGXkuo1qiE?si=cRws4H4c5JXBiZX5)