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

arXiv: https://arxiv.org/abs/2601.05487 · HTML: https://mlsanity.com/paper/2601.05487/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Builds on (most cited first, 8 of 8)

- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [DeepAnalyze: Agentic Large Language Models for Autonomous Data Science](https://mlsanity.com/paper/2510.16872/) (2025)
- [MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation](https://mlsanity.com/paper/2403.04945/) (2024)
- [DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts](https://mlsanity.com/paper/2408.05346/) (2024)
- [Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework](https://mlsanity.com/paper/2506.02454/) (2025)
- [Core Context Aware Transformers for Long Context Language Modeling](https://mlsanity.com/paper/2412.12465/) (2024)
- [FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation](https://mlsanity.com/paper/2511.07322/) (2025)

## Built on by (most cited first, 2 of 2)

- [Monte Carlo Tree Search for Table-to-Multimodal Report Generation](https://mlsanity.com/paper/2608.04071/) (2026)
- [ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence](https://mlsanity.com/paper/2605.13034/) (2026)

## Abstract (arXiv)

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 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 Data-Augmented Analysis Agent, equipped with Exploratory Data Analysis (EDA)-derived knowledge and access to raw tables, and a 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.