EvidFuse: Writing-Time Evidence Learning for Consistent Text-Chart Data Reporting

TL;DR

EvidFuse introduces a novel, training-free multi-agent framework that enables dynamic, writing-time interleaved generation of text and charts in data reports, improving consistency and insight depth.

Contribution

The paper presents EvidFuse, a new multi-agent approach that decouples visualization analysis from report drafting, allowing real-time, evidence-driven narrative generation without additional training.

Findings

Achieves top performance in chart quality and alignment

Outperforms baselines in human evaluations

Enhances report usefulness and consistency

Abstract

Data-driven reports communicate decision-relevant insights by tightly interleaving narrative text with charts grounded in underlying tables. However, current LLM-based systems typically generate narratives and visualizations in staged pipelines, following either a text-first-graph-second or a graph-first-text-second paradigm. These designs often lead to chart-text inconsistency and insight freezing, where the intermediate evidence space becomes fixed and the model can no longer retrieve or construct new visual evidence as the narrative evolves, resulting in shallow and predefined analysis. To address the limitations, we propose \textbf{EvidFuse}, a training-free multi-agent framework that enables writing-time text-chart interleaved generation for data-driven reports. EvidFuse decouples visualization analysis from long-form drafting via two collaborating components: a \textbf{Data-Augmented Analysis Agent}, equipped with Exploratory Data Analysis (EDA)-derived knowledge and access to raw tables, and a \textbf{Real-Time Evidence Construction Writer} that plans an outline and drafts the report while intermittently issuing fine-grained analysis requests. This design allows visual evidence to be constructed and incorporated exactly when the narrative requires it, directly constraining subsequent claims and enabling on-demand expansion of the evidence space. Experiments demonstrate that EvidFuse attains the top rank in both LLM-as-a-judge and human evaluations on chart quality, chart-text alignment, and report-level usefulness.