AI Agent Framework Generates Data-Driven News Stories with Verifiable Evidence Tracing
Researchers introduced Data2Story, a multi-agent AI system designed to automatically produce data journalism articles from raw information, similar to how human newsroom teams work. The system links all claims, statistics, and visuals back to verifiable sources and generates multimodal content tailored to different story types. In evaluation against 18 published articles, the AI produced competitive stories with strong transparency and auditability, though human journalists retained advantages in editorial angle and creative design.
Data2Story is a multi-agent framework that orchestrates specialized AI roles to function as a virtual newsroom, automating the data journalism process from raw data to finished multimedia articles. The system's key innovation is an Inspector component that grounds every claim, number, and visual asset in verifiable data, code, or external references, addressing a critical challenge in automated reporting. Rather than producing only text and static charts, Data2Story reasons about optimal presentation formats and deploys interactive tools such as maps for geographic stories and audio for music-related content. Evaluation across 18 articles using human rubrics (53 participants), computer-use agent judges, and code verification showed the system excels at transparency and auditability while producing stories competitive with expert human work. The researchers position Data2Story as a collaborative tool to enhance evidence-based and verifiable journalism rather than replace human reporters.
What's missing
The study does not discuss potential limitations regarding the types of data stories the system can handle (e.g., investigative journalism requiring original reporting), scalability to real-time news cycles, or how the system performs on stories requiring human sources and interviews rather than structured data.
What different sources said
- arXiv cs.CLCenter
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.