LLM system autonomously generates disease forecasting software

Researchers have developed an autonomous system that uses Large Language Models (LLMs) to generate and optimize disease forecasting software. This LLM-guided tree search approach iteratively creates, evaluates, and refines executable forecasting models. During the 2025-2026 respiratory season, the system autonomously produced diverse models for influenza, COVID-19, and RSV, with the aggregated ensemble matching or surpassing the CDC's human-curated forecasts. The framework aims to overcome the bottleneck of manual model curation, enabling scalable and rapid deployment of expert-level disease forecasting. AI

IMPACT Automates the creation of expert-level disease forecasting models, enabling rapid deployment at unprecedented scales.

RANK_REASON The cluster contains an academic paper detailing a new methodology for disease forecasting using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• COVID-19
• influenza
• Large Language Models
• LLM-guided tree search
• Centers for Disease Control and Prevention

• paper
• product
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →