The field of machine learning engineering is witnessing a significant shift towards the adoption of large language models (LLMs) for automating various tasks. Recent developments have focused on enhancing the capabilities of LLMs to perform complex tasks such as feature engineering, data analysis, and model implementation. Notably, researchers are exploring novel approaches to guide LLMs in discovering informative features, selecting effective task-specific models, and refining their performance through targeted refinement strategies. These advancements have the potential to revolutionize the field of machine learning engineering by enabling more efficient and effective model development. Noteworthy papers include: MLE-STAR, which proposes a novel approach to building MLE agents that leverages external knowledge and targeted refinement to achieve state-of-the-art performance. The work on Tabular Feature Discovery With Reasoning Type Exploration is also noteworthy, as it presents a method for guiding LLMs to discover diverse and informative features by leveraging multiple types of reasoning.