Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systems

Vaishali Dhanoa; Anton Sutje Wolter; Gabriela Molina León; Hans-Jörg Schulz; Niklas Elmqvist

doi:10.1109/MCG.2025.3607741

Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systems

^*Corresponding author af dette arbejde

Institut for Datalogi

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

Abstract

Autonomous agents powered by large language models are transforming artificial intelligence (AI), creating an imperative for the visualization area. However, our fieldBBs focus on a human in the sensemaking loop raises critical questions about autonomy, delegation, and coordination for such agentic visualization that preserve human agency while amplifying analytical capabilities. This article addresses these questions by reinterpreting existing visualization systems with semiautomated or fully automatic AI components through an agentic lens. Based on this analysis, we extract a collection of design patterns for agentic visualization, including agentic roles, communication, and coordination. These patterns provide a foundation for future agentic visualization systems that effectively harness AI agents while maintaining human insight and control.

Originalsprog	Engelsk
Tidsskrift	IEEE Computer Graphics and Applications
Vol/bind	45
Nummer	6
Sider (fra-til)	89-100
Antal sider	12
ISSN	0272-1716
DOI	https://doi.org/10.1109/MCG.2025.3607741
Status	Udgivet - 2025

Adgang til dokumentet

10.1109/MCG.2025.3607741Licens: Ikke-specificeret

Biblioteksadgang?

Tjek tilgængelighed hos det Kgl. Bibliotek

Andre filer og links

Link to publication in Scopus

Citationsformater

@article{ce756073e35541219fcd46074dec94c6,

title = "Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systems",

abstract = "Autonomous agents powered by large language models are transforming artificial intelligence (AI), creating an imperative for the visualization area. However, our fieldBBs focus on a human in the sensemaking loop raises critical questions about autonomy, delegation, and coordination for such agentic visualization that preserve human agency while amplifying analytical capabilities. This article addresses these questions by reinterpreting existing visualization systems with semiautomated or fully automatic AI components through an agentic lens. Based on this analysis, we extract a collection of design patterns for agentic visualization, including agentic roles, communication, and coordination. These patterns provide a foundation for future agentic visualization systems that effectively harness AI agents while maintaining human insight and control.",

author = "Vaishali Dhanoa and Wolter, \{Anton Sutje\} and \{Molina Le{\'o}n\}, Gabriela and Hans-J{\"o}rg Schulz and Niklas Elmqvist",

year = "2025",

doi = "10.1109/MCG.2025.3607741",

language = "English",

volume = "45",

pages = "89--100",

journal = "IEEE Computer Graphics and Applications",

issn = "0272-1716",

publisher = "IEEE Computer Society",

number = "6",

}

Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systems. / Dhanoa, Vaishali ; Wolter, Anton Sutje ; Molina León, Gabriela et al.
I: IEEE Computer Graphics and Applications, Bind 45, Nr. 6, 2025, s. 89-100.

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

TY - JOUR

T1 - Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systems

AU - Dhanoa, Vaishali

AU - Wolter, Anton Sutje

AU - Molina León, Gabriela

AU - Schulz, Hans-Jörg

AU - Elmqvist, Niklas

PY - 2025

Y1 - 2025

N2 - Autonomous agents powered by large language models are transforming artificial intelligence (AI), creating an imperative for the visualization area. However, our fieldBBs focus on a human in the sensemaking loop raises critical questions about autonomy, delegation, and coordination for such agentic visualization that preserve human agency while amplifying analytical capabilities. This article addresses these questions by reinterpreting existing visualization systems with semiautomated or fully automatic AI components through an agentic lens. Based on this analysis, we extract a collection of design patterns for agentic visualization, including agentic roles, communication, and coordination. These patterns provide a foundation for future agentic visualization systems that effectively harness AI agents while maintaining human insight and control.

AB - Autonomous agents powered by large language models are transforming artificial intelligence (AI), creating an imperative for the visualization area. However, our fieldBBs focus on a human in the sensemaking loop raises critical questions about autonomy, delegation, and coordination for such agentic visualization that preserve human agency while amplifying analytical capabilities. This article addresses these questions by reinterpreting existing visualization systems with semiautomated or fully automatic AI components through an agentic lens. Based on this analysis, we extract a collection of design patterns for agentic visualization, including agentic roles, communication, and coordination. These patterns provide a foundation for future agentic visualization systems that effectively harness AI agents while maintaining human insight and control.

UR - https://www.scopus.com/pages/publications/105015396692

U2 - 10.1109/MCG.2025.3607741

DO - 10.1109/MCG.2025.3607741

M3 - Journal article

C2 - 40924522

SN - 0272-1716

VL - 45

SP - 89

EP - 100

JO - IEEE Computer Graphics and Applications

JF - IEEE Computer Graphics and Applications

IS - 6

ER -

Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systems

Abstract

Adgang til dokumentet

Biblioteksadgang?

Andre filer og links

Fingeraftryk

Citationsformater