Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gyarmati, Péter Ferenc, Moritz, Dominik, Möller, Torsten, Koesten, Laura
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.05721
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914141887791104
author Gyarmati, Péter Ferenc
Moritz, Dominik
Möller, Torsten
Koesten, Laura
author_facet Gyarmati, Péter Ferenc
Moritz, Dominik
Möller, Torsten
Koesten, Laura
contents To address the brittleness of monolithic AI agents, our prototype for automated visual data reporting explores a Human-AI Partnership model. Its hybrid, multi-agent architecture strategically externalizes logic from LLMs to deterministic modules, leveraging the rule-based system Draco for principled visualization design. The system delivers a dual-output: an interactive Observable report with Mosaic for reader exploration, and executable Marimo notebooks for deep, analyst-facing traceability. This granular architecture yields a fully automatic yet auditable and steerable system, charting a path toward a more synergistic partnership between human experts and AI. For reproducibility, our implementation and examples are available at https://peter-gy.github.io/VISxGenAI-2025/.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05721
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Composable Agentic System for Automated Visual Data Reporting
Gyarmati, Péter Ferenc
Moritz, Dominik
Möller, Torsten
Koesten, Laura
Human-Computer Interaction
To address the brittleness of monolithic AI agents, our prototype for automated visual data reporting explores a Human-AI Partnership model. Its hybrid, multi-agent architecture strategically externalizes logic from LLMs to deterministic modules, leveraging the rule-based system Draco for principled visualization design. The system delivers a dual-output: an interactive Observable report with Mosaic for reader exploration, and executable Marimo notebooks for deep, analyst-facing traceability. This granular architecture yields a fully automatic yet auditable and steerable system, charting a path toward a more synergistic partnership between human experts and AI. For reproducibility, our implementation and examples are available at https://peter-gy.github.io/VISxGenAI-2025/.
title A Composable Agentic System for Automated Visual Data Reporting
topic Human-Computer Interaction
url https://arxiv.org/abs/2509.05721