@dair_ai: NEW paper from Meta: Agentic Discovery of Neural Architectures. This is a hot new area of research! Keep an eye on it.
Summary
Meta's new paper presents an agentic system that autonomously discovers neural architectures outperforming Llama 3.2 at 350M, 1B, and 3B scales within a 24-hour compute budget.
View Cached Full Text
Cached at: 05/19/26, 12:40 AM
NEW paper from Meta: Agentic Discovery of Neural Architectures.
This is a hot new area of research! Keep an eye on it.
elvis (@omarsar0): NEW paper from Meta.
(bookmark it)
It’s an agent system that autonomously discovers neural architectures that beat Llama 3.2 at 350M, 1B, and 3B scales, all under a 24-hour compute budget.
They get this work by splitting the search into two agents:
> AIRA-Compose searches the
Similar Articles
Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
This paper introduces AIRA-Compose and AIRA-Design, dual frameworks using AI agents to autonomously discover neural architectures that outperform standard Transformers and scale efficiently.
@dair_ai: New work from Google DeepMind and collaborators. Agentic algorithm discovery keeps getting demonstrated on problems wit…
ArchAgent v2 from Google DeepMind automates multi-level data prefetcher design using agentic algorithm discovery, outperforming hand-designed solutions in the Data Prefetching Championship.
An Agentic AI Scientific Community for Automated Neural Operator Discovery
This paper presents an agentic AI scientific community of virtual labs that autonomously discover neural operator architectures for PDE problems. Using LLM planners, numerical workers, and reviewers under a citation-based economy, the system produces high-accuracy hybrid architectures, with results suggesting no universal winner among operator families.
@dair_ai: NEW paper worth reading. A full agentic workflow can be distilled into model weights and run at roughly 100x lower infe…
This paper demonstrates that agentic workflows can be distilled into small fine-tuned models, achieving near-frontier quality while reducing inference cost by two orders of magnitude compared to orchestration approaches.
@dair_ai: New research from NVIDIA. They just dropped a PyTorch-native training framework for agentic RL. (bookmark it) Paper sum…
NVIDIA released Molt, a PyTorch-native agentic RL framework designed for compactness and readability, with performance comparable to Megatron-based stacks. The framework is open-source and includes a paper.