# City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification

arXiv: https://arxiv.org/abs/2602.19326 · HTML: https://mlsanity.com/paper/2602.19326/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 22 Feb 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills](https://mlsanity.com/paper/2504.07079/) (2025)
- [Agent AI: Surveying the Horizons of Multimodal Interaction](https://mlsanity.com/paper/2401.03568/) (2024)
- [Large Language Model for Participatory Urban Planning](https://mlsanity.com/paper/2402.17161/) (2024)
- [Reimagining City Configuration: Automated Urban Planning via Adversarial Learning](https://mlsanity.com/paper/2008.09912/) (2020)
- [Human-instructed Deep Hierarchical Generative Learning for Automated Urban Planning](https://mlsanity.com/paper/2212.00904/) (2022)
- [Deep Human-guided Conditional Variational Generative Modeling for Automated Urban Planning](https://mlsanity.com/paper/2110.07717/) (2021)
- [Automated Urban Planning for Reimagining City Configuration via Adversarial Learning: Quantification, Generation, and Evaluation](https://mlsanity.com/paper/2112.14699/) (2021)
- [Generative AI Meets Future Cities: Towards an Era of Autonomous Urban Intelligence](https://mlsanity.com/paper/2304.03892/) (2023)
- [Towards Urban Planing AI Agent in the Age of Agentic AI](https://mlsanity.com/paper/2507.14730/) (2025)
- [Dual-stage Flows-based Generative Modeling for Traceable Urban Planning](https://mlsanity.com/paper/2310.02453/) (2023)

## Built on by (most cited first, 2 of 2)

- [AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem](https://mlsanity.com/paper/2603.08938/) (2026)
- [Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing](https://mlsanity.com/paper/2610.12881/) (2026)

## Abstract (arXiv)

Urban renewal requires incremental modifications to existing geospatial plans, yet manually updating complex layouts under spatial constraints is labor-intensive and error-prone. To tackle this, we propose CEAE, a hierarchical agentic framework that formulates urban renewal as machine-executable GeoJSON editing from natural-language instructions. CEAE decomposes instructions into hierarchical geometric intents, executing edits from coarse to fine while preserving spatial consistency through a self-reflective execution-validation loop. Experimental results show that CEAE outperforms baselines in execution validity, robustness, and geometric accuracy.