In this workshop, we develop a multiple-generative agent system to simulate community decision-making for design-related affairs. Based on data from local stakeholders, our simulations incorporated varying degrees of communication, demographic data, and life values in the agent prompts. The results revealed that communication among agents improved collective reasoning. These findings highlight the potential application of AI in understanding complex social interactions and decision-making processes, offering valuable insights for urban planning, design, and society in diverse settings.

Day 1

Experimenting with the difficulties of negotiation and decision-making. Learn at a high level about how multi-agents work and their recent progress.

Setup OpenAI API

Workshop on usage of AutoGen and Github Codespace

Group formation and initial prompt design to define the problem space and start the simulation work.

Day 2

Apply the learned concepts in a simulated environment, iterating on design solutions and decision-making strategies

Summarize the workshop findings, present group projects, and discuss applications and implications of the workshop’s work.