MapStory: Prototyping Editable Map Animations with LLM Agents
Aditya Gunturu, Ben Pearman, Keiichi Ihara, Morteza Faraji, Bryan Wang, Rubaiat Habib Kazi, and Ryo Suzuki

TL;DR
MapStory is an LLM-powered tool that simplifies creating editable, animated map sequences from natural language, enabling faster, more creative map storytelling through an intuitive interface and automated geospatial data extraction.
Contribution
It introduces a dual-agent LLM architecture for generating and editing map animations directly from text, integrating geospatial querying and interactive fine-tuning.
Findings
Users can create map animations more easily and quickly.
The system facilitates creative exploration and iteration.
Expert evaluations show improved usability and lower barriers.
Abstract
We introduce MapStory, an LLM-powered animation prototyping tool that generates editable map animation sequences directly from natural language text by leveraging a dual-agent LLM architecture. Given a user written script, MapStory automatically produces a scene breakdown, which decomposes the text into key map animation primitives such as camera movements, visual highlights, and animated elements. Our system includes a researcher agent that accurately queries geospatial information by leveraging an LLM with web search, enabling automatic extraction of relevant regions, paths, and coordinates while allowing users to edit and query for changes or additional information to refine the results. Additionally, users can fine-tune parameters of these primitive blocks through an interactive timeline editor. We detail the system's design and architecture, informed by formative interviews with…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
