Generate, Validate, Repair: Reliable Visual Data Reporting with LLM Agents
Naga Datha Saikiran Battula (New Jersey Institute of Technology), Vrushali Koli (New Jersey Institute of Technology), Bayan Divaaniaazar (New Jersey Institute of Technology), Aritra Dasgupta (New Jersey Institute of Technology)
Links
Sign in to access the Paper PDF.
Abstract
AI agents can now analyze, synthesize, and visualize complex datasets, yet turning their outputs into a coherent narrative aligned with a reader’s expectations remains an open challenge. A single generation pass produces charts that misread the data, claims the visuals do not support, and narratives that lose coherence over a long document. We present a multi-agent system for automated visual data reporting in which every generative stage is paired with a deterministic validator that can reject its output, and failures are repaired in the same context or disclosed rather than shipped. The system organizes the validated panels into a guided narrative and renders it as an interactive report, letting readers follow the analytical thread and then explore the underlying data themselves.