SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents

2026-07-27

AI Summary

This work addresses the limitations of current extreme weather early warning systems, which rely heavily on expert judgment—resulting in high costs and poor scalability—and the inability of existing large language model (LLM) agents to support end-to-end operational workflows, as they typically handle isolated tasks. To bridge this gap, we propose the first end-to-end agent framework specifically designed for extreme weather early warning. Our approach integrates historical case retrieval, skill distillation, and multi-source meteorological forecasting to construct an executable reasoning and decision-making system. We also introduce SIREN-Bench, a dedicated benchmark for evaluating such systems. Experimental results demonstrate that our method significantly outperforms existing baselines both in individual components and across the full warning pipeline, achieving an expert-informed yet scalable solution for automated early warning.

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.

Problem

• extreme-weather early warning
• LLM agents
• end-to-end warning
• operational forecasting
• weather intelligence

Innovation

• LLM agents
• extreme-weather early warning
• experience-grounded
• SIREN-Bench
• end-to-end automation