A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Yangxinyu, Jiang, Bowen, Mallick, Tanwi, Bergerson, Joshua David, Hutchison, John K., Verner, Duane R., Branham, Jordan, Alexander, M. Ross, Ross, Robert B., Feng, Yan, Levy, Leslie-Anne, Su, Weijie, Taylor, Camillo J.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910917847941120
author Xie, Yangxinyu
Jiang, Bowen
Mallick, Tanwi
Bergerson, Joshua David
Hutchison, John K.
Verner, Duane R.
Branham, Jordan
Alexander, M. Ross
Ross, Robert B.
Feng, Yan
Levy, Leslie-Anne
Su, Weijie
Taylor, Camillo J.
author_facet Xie, Yangxinyu
Jiang, Bowen
Mallick, Tanwi
Bergerson, Joshua David
Hutchison, John K.
Verner, Duane R.
Branham, Jordan
Alexander, M. Ross
Ross, Robert B.
Feng, Yan
Levy, Leslie-Anne
Su, Weijie
Taylor, Camillo J.
contents Large language models (LLMs) are a transformational capability at the frontier of artificial intelligence and machine learning that can support decision-makers in addressing pressing societal challenges such as extreme natural hazard events. As generalized models, LLMs often struggle to provide context-specific information, particularly in areas requiring specialized knowledge. In this work we propose a retrieval-augmented generation (RAG)-based multi-agent LLM system to support analysis and decision-making in the context of natural hazards and extreme weather events. As a proof of concept, we present WildfireGPT, a specialized system focused on wildfire hazards. The architecture employs a user-centered, multi-agent design to deliver tailored risk insights across diverse stakeholder groups. By integrating natural hazard and extreme weather projection data, observational datasets, and scientific literature through an RAG framework, the system ensures both the accuracy and contextual relevance of the information it provides. Evaluation across ten expert-led case studies demonstrates that WildfireGPT significantly outperforms existing LLM-based solutions for decision support.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17200
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation
Xie, Yangxinyu
Jiang, Bowen
Mallick, Tanwi
Bergerson, Joshua David
Hutchison, John K.
Verner, Duane R.
Branham, Jordan
Alexander, M. Ross
Ross, Robert B.
Feng, Yan
Levy, Leslie-Anne
Su, Weijie
Taylor, Camillo J.
Computation and Language
Large language models (LLMs) are a transformational capability at the frontier of artificial intelligence and machine learning that can support decision-makers in addressing pressing societal challenges such as extreme natural hazard events. As generalized models, LLMs often struggle to provide context-specific information, particularly in areas requiring specialized knowledge. In this work we propose a retrieval-augmented generation (RAG)-based multi-agent LLM system to support analysis and decision-making in the context of natural hazards and extreme weather events. As a proof of concept, we present WildfireGPT, a specialized system focused on wildfire hazards. The architecture employs a user-centered, multi-agent design to deliver tailored risk insights across diverse stakeholder groups. By integrating natural hazard and extreme weather projection data, observational datasets, and scientific literature through an RAG framework, the system ensures both the accuracy and contextual relevance of the information it provides. Evaluation across ten expert-led case studies demonstrates that WildfireGPT significantly outperforms existing LLM-based solutions for decision support.
title A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation
topic Computation and Language
url https://arxiv.org/abs/2504.17200