Prospective multi-pathogen disease forecasting using autonomous LLM-guided tree search
This work addresses the labor-intensive bottleneck of manual model curation in infectious disease forecasting, enabling scalable and rapid deployment of expert-level models.
The paper presents an autonomous system using LLM-guided tree search to generate and optimize disease forecasting models, which in a prospective evaluation during the 2025-2026 US respiratory season matched or outperformed human-curated CDC ensembles for influenza, COVID-19, and RSV.
Probabilistic forecasting of infectious diseases is crucial for public health but relies on labor-intensive manual model curation by expert modeling teams. This bespoke development bottlenecks scalability to granular geographic resolutions or emerging pathogens. Here, we present an autonomous system using Large Language Model (LLM)-guided tree search to iteratively generate, evaluate, and optimize executable forecasting software. In a fully prospective, real-time evaluation during the 2025-2026 US respiratory season, the system autonomously discovered methodologically diverse models for influenza, COVID-19, and respiratory syncytial virus (RSV). Aggregating these machine-generated models yielded an ensemble that consistently matched or outperformed the gold-standard, human-curated Centers for Disease Control and Prevention (CDC) hub ensembles out-of-sample. The system successfully navigated data-scarce "cold start" scenarios for RSV. Moreover, controlled retrospective ablations revealed that optimizing log-scale distance metrics prevents reward hacking, while an automated judge-in-the-loop ensures structural fidelity to complex scientific theories. By autonomously translating epidemiological theory into accurate, transparent code, this framework overcomes the modeling labor bottleneck, enabling rapid deployment of expert-level disease forecasting at unprecedented scales.