AIDE: AI-Driven Exploration in the Space of Code
This addresses inefficiencies for engineers and scientists in ML development, though it appears incremental as it builds on existing LLM and optimization methods.
The paper tackles the tedious trial-and-error process in machine learning engineering by introducing AIDE, an AI-driven agent that frames it as a code optimization problem using tree search, achieving state-of-the-art results on benchmarks like Kaggle and OpenAI MLE-Bench.
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.