DataMagic speeds up accurate data video creation with multi-agent orchestration
DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration
Human-Computer InteractionArtificial IntelligenceDatabasesMultiagent Systems
Summary
Making videos that explain data using charts, voice descriptions, and animations usually needs many special skills and tools. The authors created DataMagic, a system that can turn raw data into these videos more easily by coordinating multiple automated parts. It uses a special way to describe everything in the video together, making sure the visuals, audio, and timing all match up and the data stays accurate. Tests show DataMagic makes better videos faster and with less effort than current large language models alone. This helps people make clear and engaging videos about data without needing advanced video editing knowledge.
What this means in practice
- •For data communication teams: Create data-driven storytelling videos quickly from raw data without deep video editing skills using automated multi-agent orchestration.
- •For business intelligence developers: Integrate automatic video creation tools that ensure synchronized narration and animations to present analytic insights effectively.
Authors
Yupeng Xie, Zhenyang Wang, Liangwei Wang, Jiayi Zhu, Zhouan Shen, Yuyu Luo
Abstract
Data videos communicate data insights through dynamic charts, voice narration, and synchronized animations, and have become a widely adopted form of data storytelling. However, producing them requires expertise in data analysis, narrative design, and video editing. Static visualization tools lack narrative and animation capabilities; authoring tools rely on pre-prepared charts rather than raw data; and pixel-level models generate videos end-to-end but cannot guarantee data accuracy or provenance. End-to-end automatic generation faces two core challenges: how to uniformly represent charts, narration, and animations together with their temporal relationships, and how to efficiently search a vast design space for narrative-coherent compositions. We present DataMagic, which authors data videos from raw tabular data through declarative multi-agent orchestration. First, the declarative specification DVSpec unifies charts, narration, and animations with data-bound references and declarative synchronization, ensuring data provenance and automatic audio-visual alignment. Second, a "Generate-then-Orchestrate" multi-agent strategy generates candidate scenes in parallel and then optimizes narrative coherence through global orchestration. DVSpec provides a shared state for three complementary interaction modes, bridging full automation with fine-grained human control. Evaluations on 109 real-world samples show that even the most advanced LLM (e.g., GPT-5) achieves only 2.13/5 with execution success rates between 48.62% and 86.24%; DataMagic improves quality to 3.89 (+83%) with success rates above 95%, with the most significant gains in animation and narrative dimensions. A user study shows that, compared to a conversational LLM workflow, DataMagic improves creation efficiency (79.7% reduction in task time) and reduces perceived cognitive load. Project page: https://github.com/HKUSTDial/DataMagic.