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

2024-12-29

AI Summary

Urban renewal faces challenges in dynamic adaptation and long-term planning. This paper proposes a closed-loop urban planning framework based on multi-agent large language models (LLMs), establishing an iterative “planning–lifestyle simulation–evaluation feedback” paradigm. Context-aware planning proposals are collaboratively generated by role-specialized LLM agents; interpretable agent-based simulation models human behavioral dynamics; and automated, multi-dimensional evaluation drives adaptive optimization. The framework introduces the first “planning–living–judgment” triadic coordination mechanism, overcoming limitations of static, one-off planning approaches. Evaluated on real-world urban datasets, it demonstrates significant improvements in proposal feasibility, livability, and responsiveness—enabling sustainable, self-adaptive decision-making for long-horizon urban renewal.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

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.

Problem

• Urban Renewal
• Dynamic Issues
• Flexible Solutions

Innovation

• Cyclic Urban Planning (CUP)
• Multi-role Intelligent System
• Dynamic Adaptation and Optimization