DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration
Authors
Yupeng Xie (The Hong Kong University of Science and Technology (Guangzhou)), ZhenYang Wang (The Hong Kong University of Science and Technology (Guangzhou)), Liangwei Wang (The Hong Kong University of Science and Technology (Guangzhou)), Jiayi ZHU (The Hong Kong University of Science and Technology (Guangzhou)), Zhouan Shen (Hong Kong University of Science and Technology (Guangzhou)), Yuyu Luo (The Hong Kong University of Science and Technology (Guangzhou))
Presentation
- Session
- How can I do this myself?
- Time
- Thursday, Nov 12, 08:48 – 09:00 (US/Eastern) · session 08:00 – 09:30
- Location
- Hall America center
Keywords
data video generation, data storytelling, multi-agent system, declarative specification, visualization
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, their production requires multidisciplinary expertise spanning 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 generation models, while capable of end-to-end synthesis, 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, a system that authors data videos from raw tabular data through declarative multi-agent orchestration, built on two core designs. 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 further serves as a shared state supporting 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 further demonstrates that, compared to a conversational LLM workflow, DataMagic significantly improves creation efficiency (79.7% reduction in task time) and reduces perceived cognitive load. Source code is available at https://github.com/HKUSTDial/DataMagic.
For Practitioners
Data journalists, visualization practitioners, data analysts, educators, and business intelligence professionals may use the design principles and workflow presented in this paper to create data videos from tabular data. In particular, the declarative representation and multi-agent orchestration approach can help them coordinate data-bound charts, narration, and animation while retaining fine-grained control over the generated result.