传染病的概率预测对于公共卫生至关重要，但依赖于专家建模团队的劳动密集型手动模型管理。这种定制开发限制了精细地理分辨率或新兴病原体的可扩展性。在这里,我们提出了一个自治系统，使用大型语言模型(LLM)引导树搜索来迭代生成,评估,并优化可执行预测软件。在 2025-2026 年美国呼吸道季节, 期间进行的完全前瞻性, 实时评估中，系统自主发现了流感, COVID-19, 和呼吸道合胞病毒(RSV) 的方法学上不同的模型。聚合这些机器生成的模型产生了一个整体，该整体始终匹配或优于黄金标准,人类策划的疾病控制和预防中心(CDC)样本外中心整体。系统成功导航了 RSV 数据稀缺的 " 冷启动" 场景。此外，, 控制的回顾性消融表明，优化对数尺度距离度量可以防止奖励黑客,，而自动循环判断则确保对复杂科学理论的结构保真度。通过自动将流行病学理论转化为准确的,透明代码,，该框架克服了建模劳动力瓶颈,，从而能够以前所未有的规模快速部署专家级疾病预测。
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.
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)