A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation Article Swipe
Yangxinyu Xie
,
Bowen Jiang
,
Tanwi Mallick
,
Joshua David Bergerson
,
John K. Hutchison
,
Duane R. Verner
,
Jordan Branham
,
M. Ross Alexander
,
Robert B. Ross
,
Yan Feng
,
Leslie-Anne Levy
,
Weijie Su
,
Camillo J. Taylor
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2504.17200
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2504.17200
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.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2504.17200
- https://arxiv.org/pdf/2504.17200
- OA Status
- green
- Cited By
- 1
- OpenAlex ID
- https://openalex.org/W4415306940
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415306940Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2504.17200Digital Object Identifier
- Title
-
A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and AdaptationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-04-24Full publication date if available
- Authors
-
Yangxinyu Xie, Bowen Jiang, Tanwi Mallick, Joshua David Bergerson, John K. Hutchison, Duane R. Verner, Jordan Branham, M. Ross Alexander, Robert B. Ross, Yan Feng, Leslie-Anne Levy, Weijie Su, Camillo J. TaylorList of authors in order
- Landing page
-
https://arxiv.org/abs/2504.17200Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2504.17200Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2504.17200Direct OA link when available
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
Full payload
| id | https://openalex.org/W4415306940 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2504.17200 |
| ids.doi | https://doi.org/10.48550/arxiv.2504.17200 |
| ids.openalex | https://openalex.org/W4415306940 |
| fwci | |
| type | preprint |
| title | A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11512 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.5898000001907349 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Anomaly Detection Techniques and Applications |
| topics[1].id | https://openalex.org/T13734 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.5098999738693237 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Advanced Computational Techniques and Applications |
| topics[2].id | https://openalex.org/T12597 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.47620001435279846 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2213 |
| topics[2].subfield.display_name | Safety, Risk, Reliability and Quality |
| topics[2].display_name | Fire Detection and Safety Systems |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2504.17200 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | cc-by-nc-sa |
| locations[0].pdf_url | https://arxiv.org/pdf/2504.17200 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-sa |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2504.17200 |
| locations[1].id | doi:10.48550/arxiv.2504.17200 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2504.17200 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5042596205 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1532-6746 |
| authorships[0].author.display_name | Yangxinyu Xie |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Xie, Yangxinyu |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5042928177 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-0913-6468 |
| authorships[1].author.display_name | Bowen Jiang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Jiang, Bowen |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5037238294 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-3716-4693 |
| authorships[2].author.display_name | Tanwi Mallick |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Mallick, Tanwi |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5028669999 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Joshua David Bergerson |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Bergerson, Joshua David |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5083352702 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | John K. Hutchison |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Hutchison, John K. |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5078253766 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Duane R. Verner |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Verner, Duane R. |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5089779522 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-5793-4846 |
| authorships[6].author.display_name | Jordan Branham |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Branham, Jordan |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5066421215 |
| authorships[7].author.orcid | https://orcid.org/0000-0003-1106-1100 |
| authorships[7].author.display_name | M. Ross Alexander |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Alexander, M. Ross |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5112106905 |
| authorships[8].author.orcid | |
| authorships[8].author.display_name | Robert B. Ross |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Ross, Robert B. |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5014345704 |
| authorships[9].author.orcid | https://orcid.org/0000-0001-6464-0785 |
| authorships[9].author.display_name | Yan Feng |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Feng, Yan |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5067117991 |
| authorships[10].author.orcid | |
| authorships[10].author.display_name | Leslie-Anne Levy |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Levy, Leslie-Anne |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5093925869 |
| authorships[11].author.orcid | |
| authorships[11].author.display_name | Weijie Su |
| authorships[11].author_position | middle |
| authorships[11].raw_author_name | Su, Weijie |
| authorships[11].is_corresponding | False |
| authorships[12].author.id | https://openalex.org/A5036660535 |
| authorships[12].author.orcid | https://orcid.org/0000-0002-9332-5087 |
| authorships[12].author.display_name | Camillo J. Taylor |
| authorships[12].author_position | last |
| authorships[12].raw_author_name | Taylor, Camillo J. |
| authorships[12].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2504.17200 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-18T00:00:00 |
| display_name | A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11512 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.5898000001907349 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Anomaly Detection Techniques and Applications |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2504.17200 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | cc-by-nc-sa |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2504.17200 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-sa |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2504.17200 |
| primary_location.id | pmh:oai:arXiv.org:2504.17200 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | cc-by-nc-sa |
| primary_location.pdf_url | https://arxiv.org/pdf/2504.17200 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-sa |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2504.17200 |
| publication_date | 2025-04-24 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 5, 53, 76, 83, 93 |
| abstract_inverted_index.As | 32, 75 |
| abstract_inverted_index.By | 106 |
| abstract_inverted_index.In | 48 |
| abstract_inverted_index.an | 121 |
| abstract_inverted_index.as | 27 |
| abstract_inverted_index.at | 8 |
| abstract_inverted_index.in | 21, 43, 65 |
| abstract_inverted_index.it | 136 |
| abstract_inverted_index.of | 11, 68, 78, 133 |
| abstract_inverted_index.on | 87 |
| abstract_inverted_index.to | 38, 60, 97 |
| abstract_inverted_index.we | 51, 80 |
| abstract_inverted_index.LLM | 58 |
| abstract_inverted_index.RAG | 122 |
| abstract_inverted_index.The | 90 |
| abstract_inverted_index.and | 14, 63, 71, 110, 117, 130 |
| abstract_inverted_index.are | 4 |
| abstract_inverted_index.can | 18 |
| abstract_inverted_index.for | 152 |
| abstract_inverted_index.ten | 140 |
| abstract_inverted_index.the | 9, 66, 124, 128, 134 |
| abstract_inverted_index.LLMs | 35 |
| abstract_inverted_index.both | 127 |
| abstract_inverted_index.case | 142 |
| abstract_inverted_index.risk | 100 |
| abstract_inverted_index.such | 26 |
| abstract_inverted_index.that | 17, 145 |
| abstract_inverted_index.this | 49 |
| abstract_inverted_index.work | 50 |
| abstract_inverted_index.Large | 0 |
| abstract_inverted_index.areas | 44 |
| abstract_inverted_index.data, | 114 |
| abstract_inverted_index.often | 36 |
| abstract_inverted_index.proof | 77 |
| abstract_inverted_index.(LLMs) | 3 |
| abstract_inverted_index.across | 102, 139 |
| abstract_inverted_index.design | 96 |
| abstract_inverted_index.hazard | 30, 109 |
| abstract_inverted_index.models | 2 |
| abstract_inverted_index.system | 59, 85, 125 |
| abstract_inverted_index.context | 67 |
| abstract_inverted_index.deliver | 98 |
| abstract_inverted_index.diverse | 103 |
| abstract_inverted_index.employs | 92 |
| abstract_inverted_index.ensures | 126 |
| abstract_inverted_index.events. | 31, 74 |
| abstract_inverted_index.extreme | 28, 72, 111 |
| abstract_inverted_index.focused | 86 |
| abstract_inverted_index.groups. | 105 |
| abstract_inverted_index.hazards | 70 |
| abstract_inverted_index.machine | 15 |
| abstract_inverted_index.models, | 34 |
| abstract_inverted_index.natural | 29, 69, 108 |
| abstract_inverted_index.present | 81 |
| abstract_inverted_index.propose | 52 |
| abstract_inverted_index.provide | 39 |
| abstract_inverted_index.studies | 143 |
| abstract_inverted_index.support | 19, 61 |
| abstract_inverted_index.through | 120 |
| abstract_inverted_index.weather | 73, 112 |
| abstract_inverted_index.accuracy | 129 |
| abstract_inverted_index.analysis | 62 |
| abstract_inverted_index.concept, | 79 |
| abstract_inverted_index.decision | 153 |
| abstract_inverted_index.existing | 149 |
| abstract_inverted_index.frontier | 10 |
| abstract_inverted_index.hazards. | 89 |
| abstract_inverted_index.insights | 101 |
| abstract_inverted_index.language | 1 |
| abstract_inverted_index.learning | 16 |
| abstract_inverted_index.pressing | 23 |
| abstract_inverted_index.societal | 24 |
| abstract_inverted_index.struggle | 37 |
| abstract_inverted_index.support. | 154 |
| abstract_inverted_index.tailored | 99 |
| abstract_inverted_index.wildfire | 88 |
| abstract_inverted_index.LLM-based | 150 |
| abstract_inverted_index.datasets, | 116 |
| abstract_inverted_index.provides. | 137 |
| abstract_inverted_index.relevance | 132 |
| abstract_inverted_index.requiring | 45 |
| abstract_inverted_index.solutions | 151 |
| abstract_inverted_index.Evaluation | 138 |
| abstract_inverted_index.addressing | 22 |
| abstract_inverted_index.artificial | 12 |
| abstract_inverted_index.capability | 7 |
| abstract_inverted_index.challenges | 25 |
| abstract_inverted_index.contextual | 131 |
| abstract_inverted_index.expert-led | 141 |
| abstract_inverted_index.framework, | 123 |
| abstract_inverted_index.generation | 55 |
| abstract_inverted_index.knowledge. | 47 |
| abstract_inverted_index.literature | 119 |
| abstract_inverted_index.projection | 113 |
| abstract_inverted_index.scientific | 118 |
| abstract_inverted_index.(RAG)-based | 56 |
| abstract_inverted_index.WildfireGPT | 146 |
| abstract_inverted_index.generalized | 33 |
| abstract_inverted_index.information | 135 |
| abstract_inverted_index.integrating | 107 |
| abstract_inverted_index.multi-agent | 57, 95 |
| abstract_inverted_index.outperforms | 148 |
| abstract_inverted_index.specialized | 46, 84 |
| abstract_inverted_index.stakeholder | 104 |
| abstract_inverted_index.WildfireGPT, | 82 |
| abstract_inverted_index.architecture | 91 |
| abstract_inverted_index.demonstrates | 144 |
| abstract_inverted_index.information, | 41 |
| abstract_inverted_index.intelligence | 13 |
| abstract_inverted_index.particularly | 42 |
| abstract_inverted_index.observational | 115 |
| abstract_inverted_index.significantly | 147 |
| abstract_inverted_index.user-centered, | 94 |
| abstract_inverted_index.decision-makers | 20 |
| abstract_inverted_index.decision-making | 64 |
| abstract_inverted_index.context-specific | 40 |
| abstract_inverted_index.transformational | 6 |
| abstract_inverted_index.retrieval-augmented | 54 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 13 |
| citation_normalized_percentile |