AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
Abstract
AI research agents are demonstrating great potential to accelerate scientific progress by automating the design, implementation, and training of machine learning models. We focus on methods for improving agents' performance on MLE-bench, a challenging benchmark where agents compete in Kaggle competitions to solve real-world machine learning problems. We formalize AI research agents as search policies that navigate a space of candidate solutions, iteratively modifying them using operators. By designing and systematically varying different operator sets and search policies (Greedy, MCTS, Evolutionary), we show that their interplay is critical for achieving high performance. Our best pairing of search strategy and operator set achieves a state-of-the-art result on MLE-bench lite, increasing the success rate of achieving a Kaggle medal from 39.6% to 47.7%. Our investigation underscores the importance of jointly considering the search strategy, operator design, and evaluation methodology in advancing automated machine learning.
Cite
@article{arxiv.2507.02554,
title = {AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench},
author = {Edan Toledo and Karen Hambardzumyan and Martin Josifoski and Rishi Hazra and Nicolas Baldwin and Alexis Audran-Reiss and Michael Kuchnik and Despoina Magka and Minqi Jiang and Alisia Maria Lupidi and Andrei Lupu and Roberta Raileanu and Kelvin Niu and Tatiana Shavrina and Jean-Christophe Gagnon-Audet and Michael Shvartsman and Shagun Sodhani and Alexander H. Miller and Abhishek Charnalia and Derek Dunfield and Carole-Jean Wu and Pontus Stenetorp and Nicola Cancedda and Jakob Nicolaus Foerster and Yoram Bachrach},
journal= {arXiv preprint arXiv:2507.02554},
year = {2025}
}
Comments
Code: https://github.com/facebookresearch/aira-dojo