Loading Now

Summary of Planning, Living and Judging: a Multi-agent Llm-based Framework For Cyclical Urban Planning, by Hang Ni et al.


Planning, Living and Judging: A Multi-agent LLM-based Framework for Cyclical Urban Planning

by Hang Ni, Yuzhi Wang, Hao Liu

First submitted to arxiv on: 29 Dec 2024

Categories

  • Main: Artificial Intelligence (cs.AI)
  • Secondary: Machine Learning (cs.LG)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
Cyclical Urban Planning (CUP) is a novel paradigm that leverages large language models (LLMs) to generate, evaluate, and refine urban plans in a closed-loop. The multi-agent LLM-based framework consists of three components: Planning, where agents generate and refine urban plans based on contextual data; Living, which simulates resident behaviors and interactions; and Judging, which evaluates plan effectiveness and provides feedback for improvement. This cyclical process enables a dynamic and responsive planning approach, as demonstrated by experiments on a real-world dataset.
Low GrooveSquid.com (original content) Low Difficulty Summary
Urban regeneration is a big challenge! Cities are constantly changing, so we need new ways to plan for the future. Our Cyclical Urban Planning (CUP) idea uses special computer models called large language models (LLMs). These models help us create and improve urban plans in a loop. We break this process into three steps: Plan, where we come up with ideas; Live, where we pretend to be city residents; and Judge, where we see how well our plan works and make it better. This way of planning is always changing and adapting to the needs of cities.

Keywords

» Artificial intelligence