Planning, Living and Judging: A Multi-agent LLM-based Framework for Cyclical Urban Planning
This addresses urban planning challenges for cities and planners by offering a dynamic, closed-loop approach, though it appears incremental in applying LLMs to a specific domain.
The paper tackles the challenge of urban regeneration by proposing Cyclical Urban Planning (CUP), a new paradigm that uses a multi-agent LLM-based framework to continuously generate, evaluate, and refine urban plans, with experiments on a real-world dataset demonstrating its effectiveness as an adaptive process.
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.