Prospective multi-pathogen disease forecasting using autonomous LLM-guided tree search
Empirical Research Assistance (ERA) is an autonomous system that uses a Large Language Model to automatically generate, test, and optimize executable forecasting software for influenza, COVID-19, and RSV in real-time. ERA's generated models outperformed official CDC forecasts in a live prediction challenge. This framework scales expert epidemiological modeling by automating the process of creating high-quality disease predictions.