AIBullisharXiv – CS AI · Mar 36/108
🧠
Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search
Researchers introduced GOME, an AI agent that uses gradient-based optimization instead of tree search for machine learning engineering tasks, achieving 35.1% success rate on MLE-Bench. The study shows gradient-based approaches outperform tree search as AI reasoning capabilities improve, suggesting this method will become more effective as LLMs advance.