Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories

The paper introduces Data Journalist Agent (Data2Story), a multi‑agent framework that orchestrates specialized roles into a single virtual newsroom to produce evidence‑grounded, multimodal news stories. It ensures every claim is traceable to data, code, or external references via an Inspector, and generates interactive visualizations such as maps and audio to match reader interests. Evaluations on 18 articles show competitive performance in angle coverage, rubric scores, and verifiability, while human writers still lead in editorial angle and creative design.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• agents
• multimodal