Paper Overview
Field: NLP Authors: Kevin Qinghong Lin, Batu EI, Yuhong Shi, Pan Lu, Philip Torr, James Zou Posted: 2026-06-09 arXiv: 2606.11176
Abstract (translated)
Data2Story is a multi-agent data journalism framework that orchestrates professional roles into a single virtual newsroom. Two major innovations: (1) every claim is evidence-grounded — an Inspector links each number, angle, and asset back to the data, code, or an external reference; (2) articles are generated multimodally, deploying interactive maps, audio, and other multimodal tools. Evaluated on 18 articles, it stands out in transparency and auditability, positioned as a collaborator for journalists.
Original Abstract
Data tells stories that shape society; the data journalist's job is to turn raw information into stories non-experts can trust. A high-quality news feature takes a newsroom team weeks: hunting for context, running statistics, choosing an angle, and designing visuals. Recent agents handle individual steps well: data-science agents close the analysis loop, while design agents synthesize beautiful websites. But can an agent serve as a data journalist end to end? We introduce Data Journalist Agent (Data2Story), a multi-agent framework that orchestrates specialized roles into a single virtual newsroom. Data2Story contributes two innovations. (i) Claims are evidence-grounded: an Inspector links every number, angle, and asset back to data, code, or an external reference. (ii) Articles are multimo... (truncated in source)
---
*Auto-collected on 2026-06-11.*