{
  "abstract": "This study explores the application of agentic artificial intelligence (AI) systems, powered by large language models (LLMs), to automate key components of post-landslide investigations. Two core tasks are addressed: extracting technical information from witness reports using a customized Retrieval-Augmented Generation (RAG) pipeline, and estimating landslide geometry from site images via fine-tuned YOLOv8 segmentation model combined with chain-of-thought (CoT) prompting in a multimodal LLM. Validation with historical landslide events shows that the information extractor produces accurate, source-attributed summaries that align closely with professional engineering reports, while the geometry estimation workflow infers landslide dimensions and debris volumes consistent with official records. By leveraging pre-trained foundation models and tool-based reasoning, agentic AI systems offer a solution to the challenge of applying data-hungry deep learning frameworks in the data-scarce domain of geotechnics. The results highlight the potential of agentic LLM-based systems to support efficient, interpretable, and scalable geohazard investigations, advancing automation in geotechnical engineering.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, 11 Yuk Choi Rd, Hung Hom, Kowloon, Hong Kong Special Administrative Region",
    "Department of Civil Engineering, National Yang Ming Chiao Tung University, Taiwan",
    "Research Organization of Information and Systems, The Institute of Statistical Mathematics, 10-3 Midori-cho, Tachikawa, Tokyo, 190-8562, Japan",
    "The Graduate University for Advanced Studies (SOKENDAI), 10-3 Midori-cho, Tachikawa, Tokyo, 190-8562, Japan"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Hansong Pang"
    },
    {
      "affs": [
        1
      ],
      "name": "Man Kong Lo",
      "orcid": "0000-0003-3381-9701"
    },
    {
      "affs": [
        0
      ],
      "name": "Yat Fai Leung",
      "orcid": "0000-0002-5995-4218"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Stephen Wu",
      "orcid": "0000-0002-7847-8106"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4p87p24n158rd.bib",
  "cited_by": 6,
  "doi": "10.1016/j.sandf.2026.101789",
  "fulltext_url": null,
  "id": "4p87p24n158rd",
  "issns": [
    "0038-0806",
    "1881-1418",
    "2524-1788"
  ],
  "landing_url": "https://doi.org/10.1016/j.sandf.2026.101789",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2308|Landslides and related hazards"
    ]
  ],
  "openalex": "W7162124951",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-05-22",
  "publisher": "Elsevier BV",
  "ris": "https://research.draconitic.com/paper/4p87p24n158rd.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T13:21:18Z",
      "native_id": "W7162124951",
      "source": "openalex",
      "url": "https://doi.org/10.1016/j.sandf.2026.101789"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "openalex:2308|Landslides and related hazards",
      "subfield": "environmental-science"
    }
  ],
  "title": "Reconstruction of landslide events in urban setting using LLM-based Agentic AI with multimodal data",
  "title_text": "Reconstruction of landslide events in urban setting using LLM-based Agentic AI with multimodal data",
  "type": "peer-reviewed",
  "updated_at": "2026-11-07T13:21:03Z",
  "url": "https://research.draconitic.com/paper/4p87p24n158rd",
  "venue": "SOILS AND FOUNDATIONS",
  "versions": []
}