CityPlanner: A Sandbox Agent for Executable Urban Planning

2026-09-08

AI Summary

本文提出CityPlanner，通过UrbanSandbox环境和原子任务强化学习方法解决城市规划中的空间优化问题，实验表明优于现有方法。

Abstract

Urban planning is a real-world spatial optimization problem that requires selecting feasible actions from large candidate spaces under practical objectives such as cost and service quality. Existing optimization and reinforcement learning methods are effective for fixed formulations, but often depend on task-specific representations and constraint handling. We propose \emph{CityPlanner}, a sandbox-agent framework for executable urban planning. CityPlanner introduces \emph{UrbanSandbox}, a unified file-based environment where agents inspect task files, generate plans, run evaluators, and revise decisions based on executable feedback. To make learning tractable, we further propose atomic-task reinforcement learning, which decomposes long sandbox trajectories into \emph{BuildPlan} for initial construction and \emph{ImprovePlan} for feedback-based refinement. Experiments on a real-world benchmark show that CityPlanner consistently outperforms heuristic, task-specific RL, and general LLM-agent baselines. Ablations verify the contributions of UrbanSandbox, atomic-task RL, and iterative deployment. We release the code and dataset at https://anonymous.4open.science/r/co-agent-C1C8

Problem

• Urban Planning
• Spatial Optimization
• Reinforcement Learning
• Task-specific Representations
• Constraint Handling

Innovation

• CityPlanner
• UrbanSandbox
• atomic-task reinforcement learning
• BuildPlan
• ImprovePlan