GenAI, Agents, and the Future of VIS

Challenge

About the Challenge

  • In parallel to soliciting the submission of relevant scientific works, the workshop hosts a mini challenge on AI agents data visualization. We invite participants to build on the existing template by developing agents with improved reasoning and coordination strategies. The objective is to generate more insightful, coherent, and visually compelling analyses of the provided dataset, in the form of a data visualization report.
    We will provide a starter kit and an evaluation server to support participants. During the testing period, you will be able to iteratively improve your agents by submitting them to the evaluation server. By the submission deadline, you will submit a technical report (up to 2 pages via the PCS system) that 1) describes how your best-performing agent was developed and 2) includes a link to its best generated report. Winning teams will receive $ thousands in cloud credits (sponsor to be announced), award certificates, and an invitation to present at the workshop. Short papers in workshop track A do not need to be linked with the challenge.
  • Get started with Challenge

Leaderboard

Finalized submissions from all participants are shown here anonymously. Feel free to have a look at what others have created!