AIDE: AI-Driven Exploration in the Space of Code

TL;DR

AIDE is an AI-powered agent that automates the trial-and-error process in machine learning engineering by framing it as a code optimization problem, leading to improved performance and efficiency.

Contribution

We introduce AIDE, a novel LLM-based agent that formulates machine learning engineering as a code optimization task using tree search, enabling more efficient exploration and solution refinement.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Effectively reuses and refines solutions to optimize code.

Demonstrates improved efficiency in machine learning engineering tasks.

Abstract

Machine learning, the foundation of modern artificial intelligence, has driven innovations that have fundamentally transformed the world. Yet, behind advancements lies a complex and often tedious process requiring labor and compute intensive iteration and experimentation. Engineers and scientists developing machine learning models spend much of their time on trial-and-error tasks instead of conceptualizing innovative solutions or research hypotheses. To address this challenge, we introduce AI-Driven Exploration (AIDE), a machine learning engineering agent powered by large language models (LLMs). AIDE frames machine learning engineering as a code optimization problem, and formulates trial-and-error as a tree search in the space of potential solutions. By strategically reusing and refining promising solutions, AIDE effectively trades computational resources for enhanced performance, achieving state-of-the-art results on multiple machine learning engineering benchmarks, including our Kaggle evaluations, OpenAI MLE-Bench and METRs RE-Bench.