Multi-Agent Data Visualization and Narrative Generation

2025-08-30

AI Summary

This work addresses the low automation level of end-to-end analysis and narrative generation in data visualization, as well as insufficient transparency in human-AI collaboration. We propose a lightweight hybrid multi-agent system that synergistically integrates large language models (LLMs) with deterministic, rule-based components; critical decision logic is externalized to enhance interpretability and reliability. Modular agents specialize in data exploration, chart design, and natural-language narrative generation, supporting fine-grained editing and incremental refinement. Experiments across four heterogeneous datasets demonstrate the system’s strong generalization capability, high-quality visual-narrative output, and computational efficiency. It significantly improves both the efficiency and controllability of human-AI collaborative analysis while preserving analytical fidelity and user agency.

Technology Category

• Multiagent Systems: Teamwork
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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, multi-agent 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.

Problem

• Automating data analysis workflow from exploration to visualization
• Generating coherent visual narratives for insight communication
• Improving transparency and reliability in multi-agent systems

Innovation

• Multi-agent system automates data analysis workflow
• Hybrid architecture externalizes logic for reliability
• Granular modular outputs enable surgical modifications