CityPlanner: A Sandbox Agent for Executable Urban Planning

• URL: http://arxiv.org/abs/2609.09578v1
• Date: Wed, 09 Sep 2026 00:59:36 GMT
• Title: CityPlanner: A Sandbox Agent for Executable Urban Planning
• Abstract summary: We propose emphCityPlanner, a sandbox-agent framework for executable urban planning.<n>CityPlanner introduces emphUrbanSandbox, a unified file-based environment where agents inspect task files, generate plans, run evaluators, and revise decisions based on executable feedback.<n>Experiments on a real-world benchmark show that CityPlanner consistently outperforms existing, task-specific RL, and general LLM-agent baselines.
• Score: 19.140496033840293
• License: http://creativecommons.org/licenses/by/4.0/
• 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

Related papers

• Test-Time Trajectory Optimization for Autonomous Driving [77.87162309994567]
  End-to-end planners for autonomous driving typically generate a set of candidate trajectories, score each one, and return the highest-scoring candidate.<n>We treat the scorer as a learned trajectory-level reward function and search for trajectories that maximize it.<n>Our method, TOAD, runs the Cross-Entropy Method at test time, warm-started from the planner's proposals.
  arXiv  Detail & Related papers  (2026-06-05T11:39:27Z)
• PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models [52.48858778580074]
  Planning is a fundamental capability for large language models (LLMs)<n>PlanningBench is a framework for generating scalable, diverse, verifiable planning data for both evaluation and training.
  arXiv  Detail & Related papers  (2026-05-20T08:10:15Z)
• Bridging Planning and Execution: Multi-Agent Path Finding Under Real-World Deadlines [9.228609005424348]
  We propose REMAP, an execution-informed MAPF planning framework for time-sensitive applications.<n>Our framework integrates the proposed ExecTimeNet to accurately estimate execution time based on planned paths.<n>Experiments show that REMAP achieves up to 20% improvement in solution quality over baseline methods.
  arXiv  Detail & Related papers  (2025-11-26T20:08:52Z)
• A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks [66.86312354478478]
  Agents based on large language models (LLMs) struggle with brainless trial-and-error and generating hallucinatory actions due to a lack of global planning in long-horizon tasks.<n>We introduce a plan-and-execute framework and propose a planner training method to enhance the executor agent's planning abilities without human effort.<n>Experiments show that executor agents equipped with our planner outperform existing methods, achieving new state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-10-07T06:10:53Z)
• Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints [39.01715254437105]
  This paper introduces the Multiple Aspects of Planning (MAoP) to solve planning problems with multifaceted constraints.<n>Instead of direct planning, MAoP leverages the strategist to conduct pre-planning from various aspects and provide the planning blueprint for planners.
  arXiv  Detail & Related papers  (2025-06-14T09:37:59Z)
• PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilities [7.36760703426119]
  Planning is central to agents and agentic AI.<n>To date, a comprehensive understanding of existing planning benchmarks appears to be lacking.<n>In this paper, we examine a range of planning benchmarks to identify commonly used testbeds for algorithm development.
  arXiv  Detail & Related papers  (2025-04-21T00:02:50Z)
• CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space [35.223263448229716]
  Embodied Question Answering (EQA) has primarily focused on indoor environments.<n>We introduce CityEQA, a new task where an embodied agent answers open-vocabulary questions through active exploration in dynamic city spaces.<n>We present CityEQA-EC, the first benchmark dataset featuring 1,412 human-annotated tasks.<n>We also propose Planner-Manager-Actor (PMA), a novel agent tailored for CityEQA.
  arXiv  Detail & Related papers  (2025-02-18T04:36:15Z)
• DHP: Discrete Hierarchical Planning for Hierarchical Reinforcement Learning Agents [2.1438108757511958]
  We propose a method that replaces continuous distance estimates with discrete reachability checks to evaluate subgoal feasibility.<n>Experiments in 25-room navigation environments demonstrate $100%$ success rate.<n>The method also generalizes to momentum-based control tasks and requires only $log N$ steps for replanning.
  arXiv  Detail & Related papers  (2025-02-04T03:05:55Z)
• Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following [62.10809033451526]
  This work focuses on building a task planner for Embodied Instruction Following (EIF) using Large Language Models (LLMs)<n>We frame the task as a Partially Observable Markov Decision Process (POMDP) and aim to develop a robust planner under a few-shot assumption.<n>Our experiments on the ALFRED dataset indicate that our planner achieves competitive performance under a few-shot assumption.
  arXiv  Detail & Related papers  (2024-12-27T10:05:45Z)
• AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation [81.32722475387364]
  Large Language Model-based agents have garnered significant attention and are becoming increasingly popular.<n>Planning ability is a crucial component of an LLM-based agent, which generally entails achieving a desired goal from an initial state.<n>Recent studies have demonstrated that utilizing expert-level trajectory for instruction-tuning LLMs effectively enhances their planning capabilities.
  arXiv  Detail & Related papers  (2024-08-01T17:59:46Z)
• AI planning in the imagination: High-level planning on learned abstract search spaces [68.75684174531962]
  We propose a new method, called PiZero, that gives an agent the ability to plan in an abstract search space that the agent learns during training. We evaluate our method on multiple domains, including the traveling salesman problem, Sokoban, 2048, the facility location problem, and Pacman.
  arXiv  Detail & Related papers  (2023-08-16T22:47:16Z)
• Automated Urban Planning aware Spatial Hierarchies and Human Instructions [33.06221365923015]
  We propose a novel, deep, human-instructed urban planner based on generative adversarial networks (GANs) GANs build urban functional zones based on information from human instructions and surrounding contexts. We conduct extensive experiments to validate the efficacy of our work.
  arXiv  Detail & Related papers  (2022-09-26T20:37:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.