DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration

Hugging Face Daily Papers Papers
multi-agent data-video llm-orchestration visualization human-computer-interaction declarative-specification

Summary

DataMagic introduces a declarative multi-agent orchestration framework (DVSpec) that turns raw tabular data into narrated data videos, improving quality from 2.13/5 to 3.89/5 over GPT-5 baselines and cutting task time by 79.7% in user studies.

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.
Original Article
View Cached Full Text

Cached at: 10/02/26, 08:27 AM

Paper page - DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration

Source: https://huggingface.co/papers/2609.33403

Abstract

Datavideoscommunicatedatainsightsthroughdynamiccharts,voicenarration,andsynchronizedanimations,andhavebecomeawidelyadoptedformofdatastorytelling.However,producingthemrequiresexpertiseindataanalysis,narrativedesign,andvideoediting.Staticvisualizationtoolslacknarrativeandanimationcapabilities;authoringtoolsrelyonpre-preparedchartsratherthanrawdata;andpixel-levelmodelsgeneratevideosend-to-endbutcannotguaranteedataaccuracyorprovenance.End-to-endautomaticgenerationfacestwocorechallenges:howtouniformlyrepresentcharts,narration,andanimationstogetherwiththeirtemporalrelationships,andhowtoefficientlysearchavastdesignspacefornarrative-coherentcompositions.WepresentDataMagic,whichauthorsdatavideosfromrawtabulardatathroughdeclarativemulti-agentorchestration.First,thedeclarativespecificationDVSpecunifiescharts,narration,andanimationswithdata-boundreferencesanddeclarativesynchronization,ensuringdataprovenanceandautomaticaudio-visualalignment.Second,a“Generate-then-Orchestrate“multi-agentstrategygeneratescandidatescenesinparallelandthenoptimizesnarrativecoherencethroughglobalorchestration.DVSpecprovidesasharedstateforthreecomplementaryinteractionmodes,bridgingfullautomationwithfine-grainedhumancontrol.Evaluationson109real-worldsamplesshowthateventhemostadvancedLLM(e.g.,GPT-5)achievesonly2.13/5withexecutionsuccessratesbetween48.62%and86.24%;DataMagicimprovesqualityto3.89(+83%)withsuccessratesabove95%,withthemostsignificantgainsinanimationandnarrativedimensions.Auserstudyshowsthat,comparedtoaconversationalLLMworkflow,DataMagicimprovescreationefficiency(79.7%reductionintasktime)andreducesperceivedcognitiveload.Projectpage:https://github.com/HKUSTDial/DataMagic.

View arXiv pageView PDFProject pageGitHub275Add to collection

Get this paper in your agent:

hf papers read 2609\.33403

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.33403 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.33403 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.33403 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

CuratorMAS: Automating Dataset Curation via Multi-Agent Orchestration

arXiv cs.AI

CuratorMAS proposes a multi-agent orchestration framework that automates dataset curation through five programmable stages—exploration, knowledge retrieval, evaluation, filtering, and skill evolution—reducing noise rates by up to 36.03 pp and improving downstream F1 scores by up to 8.88 pp.

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent

Hugging Face Daily Papers

Video-DeepResearch (Video-DR) extends multimodal agents from static images to continuous video streams, introducing a decoupled perception-exploration pipeline and a new benchmark Video-DR-Bench. Their Video-DeepResearch-35B-A3B model achieves 64.0% accuracy, surpassing Claude-4.5-Sonnet, GPT-5, and Gemini 2.5 Pro.