Sentence to Model: Cost-Effective Data Collection LLM Agent

We introduce Sentence-to-Model, an automated system that converts natural language queries into tabular datasets and predictive models. The system utilizes LLM agents for planning and active learning to prioritize data collection under budget constraints, such as API costs and rate limits. By integrating resources, it generates datasets and trains machine learning models with minimal human intervention. Sentence-to-Model streamlines data collection and enables the refinement of user needs and easy exploration of the data landscape. Our approach highlights the potential of combining LLMs with algorithmic techniques for efficient data science workflows.