Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Researchers introduced OpenMLE, an open system for studying recursive self-improvement in machine learning engineering.

Frontis-MA1 was further trained with execution-grounded supervised fine-tuning and reinforcement learning around four program-evolution operators.

The model improved on MLE-Bench Lite and showed transfer gains on NatureBench Lite.

The team also released the model weights and full stack to support reproducible research.