mlsanityData to 14 Oct 2026

CityPlanner: A Sandbox Agent for Executable Urban Planning

arXiv 2609.09578 ↗First posted 9 Sep 2026cs.AI cs.CLcited by 0

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

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 CityPlanner, a sandbox-agent framework for executable urban planning. CityPlanner introduces 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 BuildPlan for initial construction and 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

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 13 of its 27 references that are in the map. First posted on arXiv 9 Sep 2026.

Builds on

13 of 27 references.

References · 13

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  3. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  4. 2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 1,040
  5. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 392
  6. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  7. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 268
  8. 2025Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planningcited by 17
  9. 2025Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environmentscited by 17
  10. 2024UrbanLLM: Autonomous Urban Activity Planning and Management with Large Language Modelscited by 13
  11. 2026Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based Evaluationcited by 13
  12. 2025Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agentscited by 12
1 more
  1. 2024Large language model empowered participatory urban planningcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning Is All You Need for Urban Planning AI
  2. 2026CityReal: Human-Aligned Urban Behavior and City Dynamics Simulation with Large-Scale LLM Agents
  3. 2026Intelli-Planner: Towards Customized Urban Planning via Large Language Model Empowered Reinforcement Learning
  4. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agents
  5. 2024LiPUP-MA: A Residential Experience-centric Multi-Agent Framework for Living-in-the-loop Participatory Urban Planning
  6. 2026GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning
  7. 2025PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilities
  8. 2026Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents