AIBuildAI: An AI Agent for Automatically Building AI Models
Ruiyi Zhang, Peijia Qin, Qi Cao, Li Zhang, Pengtao Xie

TL;DR
AIBuildAI is an AI agent that automates the entire AI model development process from task description to deployment, surpassing existing AutoML methods in versatility and performance.
Contribution
The paper introduces a hierarchical AI agent system that automates full AI model development, integrating multiple specialized LLM-based sub-agents for end-to-end automation.
Findings
AIBuildAI ranks first on MLE-Bench with 63.1% medal rate.
It outperforms all baseline methods on diverse AI tasks.
It matches the capabilities of experienced AI engineers.
Abstract
AI models underpin modern intelligent systems, driving advances across science, medicine, finance, and technology. Yet developing high-performing AI models remains a labor-intensive process that requires expert practitioners to iteratively design architectures, engineer representations, implement training pipelines and refine approaches through empirical evaluation. Existing AutoML methods partially alleviate this burden but remain limited to narrow aspects such as hyperparameter optimization and model selection within predefined search spaces, leaving the full development lifecycle largely dependent on human expertise. To address this gap, we introduce AIBuildAI, an AI agent that automatically builds AI models from a task description and training data. AIBuildAI adopts a hierarchical agent architecture in which a manager agent coordinates three specialized sub-agents: a designer for…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
