Score: 1

A Composable Agentic System for Automated Visual Data Reporting

Published: September 6, 2025 | arXiv ID: 2509.05721v1

By: Péter Ferenc Gyarmati , Dominik Moritz , Torsten Möller and more

Potential Business Impact:

AI and people work together to make reports.

Business Areas:
Artificial Intelligence Artificial Intelligence, Data and Analytics, Science and Engineering, Software

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/.

Country of Origin
🇦🇹 🇺🇸 🇦🇪 United Arab Emirates, United States, Austria

Page Count
3 pages

Category
Computer Science:
Human-Computer Interaction