Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories

arXiv:2606.11176 · cs.CV, cs.CL, cs.CY, cs.HC · Submitted 2026-06-09 · Read on arXiv

cs.CV, cs.CL, cs.CY, cs.HC

Submitted: 2026-06-09

Updated: 2026-09-17

Comments: Project page: https://data2story.github.io Github: https://github.com/QinghongLin/data2story-skill

Code: https://github.com/QinghongLin/data2story-skill

Project page: https://data2story.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Provenance — 11× in this paper · explained in 4 episodes
• Verifiability — 10× in this paper · explained in 2 episodes
• Verifier — 9× in this paper · explained in 2 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Trace — 5× in this paper · explained in 2 episodes
• Agent-as-Judge — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Multi-Agent Framework — 4× in this paper · explained in 3 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Accountability — 2× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Empirical Methods in Natural Language Processing — 2× in this paper
• Generative AI — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• In International Conference on Learning Representations — 2× in this paper
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Multi-Agent System — 2× in this paper · explained in 6 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Diagnostic Tools — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
• ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
• MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
• MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
• CoDA: Agentic Systems for Collaborative Data Visualization
• MindSearch: Mimicking Human Minds Elicits Deep AI Searcher
• MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines
• DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
• DSGym: A Holistic Framework for Evaluating and Training Data Science Agents
• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
• The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
• BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
• DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments
• OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
• DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts
• DeepAnalyze: Agentic Large Language Models for Autonomous Data Science
• PublicAgent: Multi-Agent Design Principles From an LLM-Based Open Data Analysis Framework
• Developing Story: Case Studies of Generative AI's Use in Journalism
• LLMs as Science Journalists: Supporting Early-stage Researchers in Communicating Their Science to the Public
• From Data to Story: Towards Automatic Animated Data Video Creation with LLM-based Multi-Agent Systems

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models