A2P-Vis: an Analyzer-to-Presenter Agentic Pipeline for Visual Insights Generation and Reporting

TL;DR

The paper addresses two bottlenecks in automating data science pipelines: generating diverse, evidence-rich visualizations and assembling them into a coherent, professional report. It introduces A2P-Vis, a two-part pipeline where the Data Analyzer profiles data, proposes visualization directions, generates and executes plotting code, filters low-quality figures with a legibility checker, and scores insights; the Presenter ranks topics, crafts chart-grounded narratives, and polishes the document. Key contributions include the modular double-agent design, a quality gate for charts, and an explicit insight scoring rubric to ensure depth, correctness, specificity, and actionability. The approach promises publication-ready reports with reduced manual glue work, improving practical usefulness of automated data analysis for practitioners.

Abstract

Automating end-to-end data science pipeline with AI agents still stalls on two gaps: generating insightful, diverse visual evidence and assembling it into a coherent, professional report. We present A2P-Vis, a two-part, multi-agent pipeline that turns raw datasets into a high-quality data-visualization report. The Data Analyzer orchestrates profiling, proposes diverse visualization directions, generates and executes plotting code, filters low-quality figures with a legibility checker, and elicits candidate insights that are automatically scored for depth, correctness, specificity, depth and actionability. The Presenter then orders topics, composes chart-grounded narratives from the top-ranked insights, writes justified transitions, and revises the document for clarity and consistency, yielding a coherent, publication-ready report. Together, these agents convert raw data into curated materials (charts + vetted insights) and into a readable narrative without manual glue work. We claim that by coupling a quality-assured Analyzer with a narrative Presenter, A2P-Vis operationalizes co-analysis end-to-end, improving the real-world usefulness of automated data analysis for practitioners. For the complete dataset report, please see: https://www.visagent.org/api/output/f2a3486d-2c3b-4825-98d4-5af25a819f56.

Figures (2)

• Figure 1: Data Analyzer in Action (From metadata profiling to graded insights).
• Figure 2: Presenter in Action(From ranked topics to a narrative report).