用专家经验训练的AI代理，实现极端天气预警全流程自动化。
SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents
- 基于历史案例构建可检索的智能体框架，模拟专家决策逻辑。
- 在600个任务上测试，显著优于现有气象智能体，端到端准确率提升32%。
- 适合需要快速、可扩展预警系统的气象机构与应急管理部门。
极端天气早期预警对降低社会、经济和环境风险至关重要。然而，当前以专家为中心的预警流程成本高、人力密集且难以规模化。尽管大型语言模型（LLM）智能体已能自动处理部分气象任务，但现有研究仍局限于孤立的科学任务，忽视了从监测到行动的链式依赖过程。为此，本研究探索通过LLM智能体实现端到端极端天气预警。我们首先构建SIREN-Bench，一个涵盖19项任务、600个问答实例的综合性基准，覆盖四个独立预警环节及端到端预警链。评估显示，现有气象智能体框架存在显著能力差距。由此我们提出SIREN，一种基于专家经验的智能体框架，融合异构气象证据与工具的执行环境，以及利用检索、技能蒸馏和预测建模挖掘历史案例的智能体家族。大量实验表明，SIREN在单个预警环节与端到端链路中均优于现有基线。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。