HazardWeaver: Scientific Route Selection for Hazard Analysis Agents
作者: Wangshu Zhu, Xueqi Cheng, Liang Wu, Yushun Dong
分类: cs.AI
发布日期: 2026-10-02
备注: 24 pages, including references and appendices. Code is available at https://github.com/LabRAI/HazardWeaver
🔗 代码/项目: GITHUB
💡 一句话要点
提出HazardWeaver以解决自然灾害分析中的科学路线选择问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 自然灾害分析 科学路线选择 自动化工作流程 动态决策 风险管理
📋 核心要点
- 现有方法在自然灾害分析中缺乏有效的自动化,难以选择适合的科学方法。
- HazardWeaver通过提取证据相关条件和构建科学能力图来实现科学路线选择,动态调整决策。
- 在141个实例的基准测试中,HazardWeaver在多条可选科学路线的任务中表现优异,超越现有系统。
📝 摘要(中文)
理解和评估自然灾害对于灾害准备和风险降低至关重要。近年来,大型语言模型的进展激发了对用于灾害分析的AI代理的兴趣,尤其是在将科学数据、模型和工具集成到自动化工作流程中的能力。然而,有效的自动化要求代理能够确定适合特定事件的科学方法,并能够使用可用的数据和工具。随着新证据和执行结果的出现,这些条件可能会发生变化,要求代理重新考虑其选择。为此,本文提出了HazardWeaver,通过Hazard Knowledge Compiler提取与证据相关的科学适用条件,并利用Hazard Capability Graph表示可执行的科学能力,检查其输入和输出之间的兼容性。Hazard Weaver Agent组件选择适用和可执行的路线,执行其工作流程,并在分析状态变化时修正决策。
🔬 方法详解
问题定义:本文旨在解决自然灾害分析中科学路线选择的问题。现有方法在动态环境下难以有效选择适合的科学方法,导致分析结果的准确性和可靠性不足。
核心思路:HazardWeaver的核心思路是通过构建Hazard Knowledge Compiler和Hazard Capability Graph,提取与证据相关的科学适用条件,并动态选择可执行的科学路线。这种设计使得代理能够适应不断变化的分析状态。
技术框架:HazardWeaver的整体架构包括两个主要模块:Hazard Knowledge Compiler用于提取科学适用条件,Hazard Capability Graph用于表示可执行的科学能力。Hazard Weaver Agent则负责选择和执行科学路线,并在状态变化时修正决策。
关键创新:HazardWeaver的主要创新在于引入了状态依赖的科学路线选择机制,能够根据新证据和执行结果动态调整选择,与现有静态方法形成鲜明对比。
关键设计:在设计中,Hazard Knowledge Compiler和Hazard Capability Graph的构建过程是关键,确保了输入输出的兼容性。此外,代理的决策修正机制也为动态分析提供了支持。
🖼️ 关键图片
📊 实验亮点
在141个实例的基准测试中,HazardWeaver在多条可选科学路线的任务中表现优异,整体性能超越现有代理系统,尤其在多重灾害交互类任务中,提升幅度显著,展示了其在复杂环境下的有效性。
🎯 应用场景
HazardWeaver在自然灾害分析、应急响应和风险管理等领域具有广泛的应用潜力。通过自动化科学路线选择,该系统能够提高灾害响应的效率和准确性,帮助决策者更好地应对突发事件,降低潜在损失。未来,该技术还可以扩展到其他领域,如环境监测和公共安全。
📄 摘要(原文)
Understanding and assessing natural hazards is essential for disaster preparedness and risk reduction. Recent advances in large language models have spurred growing interest in AI agents for hazard analysis, particularly their ability to integrate scientific data, models, and tools into automated workflows. However, effective automation requires agents to determine which scientific methods are appropriate for a given event and executable with the available data and tools. As new evidence and execution results become available, these conditions can change, requiring agents to reconsider their choices. We formulate this problem as state-dependent scientific route selection and introduce HazardWeaver. Specifically, HazardWeaver first leverages the Hazard Knowledge Compiler to extract evidence-linked conditions governing scientific applicability, then its Hazard Capability Graph represents executable scientific capabilities and checks compatibility between their inputs and outputs. Using these complementary representations, the Hazard Weaver Agent component selects applicable and executable routes, carries out their workflows, and revises its decisions as the analysis state changes. To evaluate both the scientific outputs and the decisions that produce them, we introduce the Hazard Weaver Benchmark, comprising 141 instances across seven single-hazard domains and four multi-hazard interaction classes. The benchmark accommodates multiple valid scientific routes and evaluates output correctness, route validity, and justified abstention. Extensive experiments on this benchmark show that HazardWeaver outperforms existing agent systems, with the largest gains on tasks with multiple eligible scientific routes. Our code is publicly available at https://github.com/LabRAI/HazardWeaver.