View in EDS HTML Full Text PDF Full Text

CartoAgent: a multimodal large language model-powered multi-agent cartographic framework for map style transfer and evaluation.

Saved in:
Bibliographic Details
Title: CartoAgent: a multimodal large language model-powered multi-agent cartographic framework for map style transfer and evaluation.
Authors: Wang, Chenglong1,2 (AUTHOR), Kang, Yuhao3,4 (AUTHOR), Gong, Zhaoya1,2 (AUTHOR) z.gong@pku.edu.cn, Zhao, Pengjun1,2 (AUTHOR), Feng, Yu5 (AUTHOR), Zhang, Wenjia6 (AUTHOR), Li, Ge7 (AUTHOR)
Source: International Journal of Geographical Information Science. Sep2025, Vol. 39 Issue 9, p1904-1937. 34p.
Subjects: Cartography, Map design, Language models, Generative artificial intelligence, Multimodal user interfaces, Aesthetics of art, Multiagent systems
Abstract: The rapid development of generative artificial intelligence (GenAI) presents new opportunities to advance the cartographic process. Previous studies have either overlooked the artistic aspects of maps or faced challenges in creating both accurate and informative maps. In this study, we propose CartoAgent, a novel multi-agent cartographic framework powered by multimodal large language models (MLLMs). This framework simulates three key stages in cartographic practice: preparation, map design, and evaluation. At each stage, different MLLMs act as agents with distinct roles to collaborate, discuss, and utilize tools for specific purposes. In particular, CartoAgent leverages MLLMs' visual aesthetic capability and world knowledge to generate maps that are both visually appealing and informative. By separating style from geographic data, it can focus on designing stylesheets without modifying the vector-based data, thereby ensuring geographic accuracy. As a result, the proposed CartoAgent could effectively produce maps that are not only visually appealing but also accurate and informative. We applied it to a specific task centered on map restyling, namely, map style transfer and evaluation. The effectiveness of this framework was validated through extensive experiments and a human evaluation study. CartoAgent can be extended to support a variety of cartographic design decisions and inform future integrations of GenAI in cartography. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Geographical Information Science is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 187437614
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: CartoAgent: a multimodal large language model-powered multi-agent cartographic framework for map style transfer and evaluation.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Wang%2C+Chenglong%22">Wang, Chenglong</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kang%2C+Yuhao%22">Kang, Yuhao</searchLink><relatesTo>3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gong%2C+Zhaoya%22">Gong, Zhaoya</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> z.gong@pku.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhao%2C+Pengjun%22">Zhao, Pengjun</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Feng%2C+Yu%22">Feng, Yu</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Wenjia%22">Zhang, Wenjia</searchLink><relatesTo>6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Ge%22">Li, Ge</searchLink><relatesTo>7</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Geographical+Information+Science%22">International Journal of Geographical Information Science</searchLink>. Sep2025, Vol. 39 Issue 9, p1904-1937. 34p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Cartography%22">Cartography</searchLink><br /><searchLink fieldCode="DE" term="%22Map+design%22">Map design</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink><br /><searchLink fieldCode="DE" term="%22Generative+artificial+intelligence%22">Generative artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Multimodal+user+interfaces%22">Multimodal user interfaces</searchLink><br /><searchLink fieldCode="DE" term="%22Aesthetics+of+art%22">Aesthetics of art</searchLink><br /><searchLink fieldCode="DE" term="%22Multiagent+systems%22">Multiagent systems</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The rapid development of generative artificial intelligence (GenAI) presents new opportunities to advance the cartographic process. Previous studies have either overlooked the artistic aspects of maps or faced challenges in creating both accurate and informative maps. In this study, we propose CartoAgent, a novel multi-agent cartographic framework powered by multimodal large language models (MLLMs). This framework simulates three key stages in cartographic practice: preparation, map design, and evaluation. At each stage, different MLLMs act as agents with distinct roles to collaborate, discuss, and utilize tools for specific purposes. In particular, CartoAgent leverages MLLMs' visual aesthetic capability and world knowledge to generate maps that are both visually appealing and informative. By separating style from geographic data, it can focus on designing stylesheets without modifying the vector-based data, thereby ensuring geographic accuracy. As a result, the proposed CartoAgent could effectively produce maps that are not only visually appealing but also accurate and informative. We applied it to a specific task centered on map restyling, namely, map style transfer and evaluation. The effectiveness of this framework was validated through extensive experiments and a human evaluation study. CartoAgent can be extended to support a variety of cartographic design decisions and inform future integrations of GenAI in cartography. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Geographical Information Science is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=187437614
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/13658816.2025.2507844
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 34
        StartPage: 1904
    Subjects:
      – SubjectFull: Cartography
        Type: general
      – SubjectFull: Map design
        Type: general
      – SubjectFull: Language models
        Type: general
      – SubjectFull: Generative artificial intelligence
        Type: general
      – SubjectFull: Multimodal user interfaces
        Type: general
      – SubjectFull: Aesthetics of art
        Type: general
      – SubjectFull: Multiagent systems
        Type: general
    Titles:
      – TitleFull: CartoAgent: a multimodal large language model-powered multi-agent cartographic framework for map style transfer and evaluation.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Wang, Chenglong
      – PersonEntity:
          Name:
            NameFull: Kang, Yuhao
      – PersonEntity:
          Name:
            NameFull: Gong, Zhaoya
      – PersonEntity:
          Name:
            NameFull: Zhao, Pengjun
      – PersonEntity:
          Name:
            NameFull: Feng, Yu
      – PersonEntity:
          Name:
            NameFull: Zhang, Wenjia
      – PersonEntity:
          Name:
            NameFull: Li, Ge
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: Sep2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 13658816
          Numbering:
            – Type: volume
              Value: 39
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: International Journal of Geographical Information Science
              Type: main
ResultId 1