Multi-Agent Data Visualization and Narrative Generation | TU Wien

Information

Publication Type: Invited Talk
Workgroup(s)/Project(s): not specified
Date: 3. November 2025
Event: 1st Workshop on Logo GenAI, Agents, and the Future of VIS (IEEE VIS 2025)
Location: Vienna
Conference date: 3. November 2025
Keywords: Multiagentensystem

Abstract

Recent advancements in the field of AI agents have impacted the way we work, enabling greater automation and collaboration between humans and agents. In the data visualization field, multiagent systems can be useful for employing agents throughout the entire data-to-communication pipeline. We present a lightweight multi-agent system that automates the data analysis workflow, from data exploration to generating coherent visual narratives for insight communication. Our approach combines a hybrid multi-agent architecture with deterministic components, strategically externalizing critical logic from LLMs to improve transparency and reliability. The system delivers granular, modular outputs that enable surgical modifications without full regeneration, supporting sustainable human-AI collaboration. We evaluated our system across 4 diverse datasets, demonstrating strong generalizability, narrative quality, and computational efficiency with minimal dependencies.

Additional Files and Images

No additional files or images.

Weblinks

Entry in reposiTUm (TU Wien Publication Database)

BibTeX

@talk{wolter-2025-mdv,
  title =      "Multi-Agent Data Visualization and Narrative Generation",
  author =     "Anton Wolter and Georgios Vidalakis and Michael Yu and Ankit
               Grover and Vaishali Dhanoa",
  year =       "2025",
  abstract =   "Recent advancements in the field of AI agents have impacted
               the way we work, enabling greater automation and
               collaboration between humans and agents. In the data
               visualization field, multiagent systems can be useful for
               employing agents throughout the entire data-to-communication
               pipeline. We present a lightweight multi-agent system that
               automates the data analysis workflow, from data exploration
               to generating coherent visual narratives for insight
               communication. Our approach combines a hybrid multi-agent
               architecture with deterministic components, strategically
               externalizing critical logic from LLMs to improve
               transparency and reliability. The system delivers granular,
               modular outputs that enable surgical modifications without
               full regeneration, supporting sustainable human-AI
               collaboration. We evaluated our system across 4 diverse
               datasets, demonstrating strong generalizability, narrative
               quality, and computational efficiency with minimal
               dependencies.",
  month =      nov,
  event =      "1st Workshop on  Logo GenAI, Agents, and the Future of VIS
               (IEEE VIS 2025)",
  location =   "Vienna",
  keywords =   "Multiagentensystem",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2025/wolter-2025-mdv/",
}