SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents
2026-07-27 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors study how to automate extreme weather warnings using advanced language models to make the process faster and less costly. They created a test called SIREN-Bench with 600 questions covering many steps in weather warning systems and found current models still struggle. To improve this, they designed SIREN, a new system that learns from past warning cases and combines multiple tools to better handle weather data. Their experiments show that SIREN performs better than existing methods both on individual tasks and the full warning process.
Extreme weather warningLarge Language Models (LLMs)SIREN-BenchAutomated weather forecastingAgentic execution environmentHistorical case retrievalSkill distillationPredictive modelingEnd-to-end warning systemsWeather evidence integration
Authors
Hang Ni, Weijia Zhang, Fan Liu, Mengqian Lu, Hao Liu
Abstract
Early warning of extreme weather is essential for mitigating the societal, economic, and environmental risks posed by hazardous weather events. However, expert-centered warning workflows are costly, labor-intensive, and difficult to scale throughout the warning-to-action process. Although recent advances in Large Language Model (LLM) agents have enabled the automation of weather-related tasks, existing studies remain centered on isolated scientific tasks and overlook the chain of interdependent processes required for operational extreme-weather early warning. To bridge this gap, this study investigates automated end-to-end extreme-weather early warning through LLM agents. We first develop SIREN-Bench, a comprehensive benchmark comprising 600 question-answer instances across 19 tasks, and covering four individual warning procedures and an end-to-end warning chain. Evaluation on SIREN-Bench reveals substantial capability gaps in existing weather agent frameworks. This motivates us to develop SIREN, an experience-grounded agent framework inspired by experts' use of historical cases, which combines an agentic execution environment integrating heterogeneous weather evidence and tools with a family of agent harnesses that exploit historical cases through retrieval, skill distillation, and predictive modeling. Extensive experiments demonstrate that SIREN outperforms weather-agent baselines on both individual warning procedures and end-to-end warning chains.