University of Tsukuba

Lottery and Sprint: Generate a Board Game with Design Sprint Method on AutoGPT

This research introduces the Lottery and Sprint methodology, a framework designed to facilitate collaborative board game creation by integrating human design intuition with the structured Design Sprint process executed by AutoGPT.

Impressions of the GDMC AI Settlement Generation Challenge in Minecraft

The Generative Design in Minecraft (GDMC) AI Settlement Generation Challenge serves as a critical platform for advancing procedural content generation (PCG) by tasking developers with creating algorithms capable of producing adaptive, holistic settlements.

• The GDMC challenge is shifting its focus from rigid competitive rankings to a qualitative festival of ideas that prioritizes human-centric evaluation and the exchange of creative processes.
• While procedural models have successfully improved structural variety and terrain adaptation, they currently struggle with functional complexities such as efficient navigation, safety, and lighting.
• The current evaluation framework inadvertently favors consistent, low-variance performance, which discourages unique or narrative-driven architectural innovation.