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

TL;DR

This paper introduces Cyclical Urban Planning (CUP), a multi-agent LLM-based framework that continuously generates, evaluates, and refines urban plans through a closed-loop process, enhancing adaptability in urban regeneration.

Contribution

The paper presents a novel multi-agent LLM framework for cyclical urban planning, integrating planning, simulation, and evaluation components for adaptive urban regeneration.

Findings

Demonstrates effectiveness of CUP on real-world datasets

Shows continuous refinement improves urban plan quality

Validates adaptability in dynamic urban contexts

Abstract

Urban regeneration presents significant challenges within the context of urbanization, requiring adaptive approaches to tackle evolving needs. Leveraging advancements in large language models (LLMs), we propose Cyclical Urban Planning (CUP), a new paradigm that continuously generates, evaluates, and refines urban plans in a closed-loop. Specifically, our multi-agent LLM-based framework consists of three key components: (1) Planning, where LLM agents generate and refine urban plans based on contextual data; (2) Living, where agents simulate the behaviors and interactions of residents, modeling life in the urban environment; and (3) Judging, which involves evaluating plan effectiveness and providing iterative feedback for improvement. The cyclical process enables a dynamic and responsive planning approach. Experiments on the real-world dataset demonstrate the effectiveness of our framework as a continuous and adaptive planning process.