MLE-bench uses 75 Kaggle competitions as offline ML engineering benchmarks
MLE-bench evaluates ML engineering agents on 75 curated offline Kaggle competitions, testing model training, dataset preparation, experiment execution, and submission to grading scripts. Kaggle public leaderboards serve as human baselines. The best-performing setup—o1-preview with AIDE scaffolding—reached at least Kaggle bronze-medal level in 16.9% of competitions.
Éléments favorables
Harness Engineering for Self-Improvement
Extrait original
MLE-bench : evaluate ML engineering agents on offline Kaggle competitions. Contains 75 ML-engineering competitions curated from Kaggle.
Contexte
Tests training models, preparing datasets, running experiments, and submitting predictions to grading scripts. Uses Kaggle public leaderboards as human baselines. Best setup in the paper, o1-preview with AIDE scaffolding, reached at least Kaggle bronze-medal level in 16.9% of competitions. Includes resource-scaling and contamination analyses.
Partager un aperçuVérifier cette affirmation