City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917298390958080 |
|---|---|
| author | Liu, Rui Quan, Steven Jige Peng, Zhong-Ren Yao, Zijun Wang, Han Chen, Zhengzhang Liu, Kunpeng Fu, Yanjie Wang, Dongjie |
| author_facet | Liu, Rui Quan, Steven Jige Peng, Zhong-Ren Yao, Zijun Wang, Han Chen, Zhengzhang Liu, Kunpeng Fu, Yanjie Wang, Dongjie |
| contents | As cities evolve over time, challenges such as traffic congestion and functional imbalance increasingly necessitate urban renewal through efficient modification of existing plans, rather than complete re-planning. In practice, even minor urban changes require substantial manual effort to redraw geospatial layouts, slowing the iterative planning and decision-making procedure. Motivated by recent advances in agentic systems and multimodal reasoning, we formulate urban renewal as a machine-executable task that iteratively modifies existing urban plans represented in structured geospatial formats. More specifically, we represent urban layouts using GeoJSON and decompose natural-language editing instructions into hierarchical geometric intents spanning polygon-, line-, and point-level operations. To coordinate interdependent edits across spatial elements and abstraction levels, we propose a hierarchical agentic framework that jointly performs multi-level planning and execution with explicit propagation of intermediate spatial constraints. We further introduce an iterative execution-validation mechanism that mitigates error accumulation and enforces global spatial consistency during multi-step editing. Extensive experiments across diverse urban editing scenarios demonstrate significant improvements in efficiency, robustness, correctness, and spatial validity over existing baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19326 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification Liu, Rui Quan, Steven Jige Peng, Zhong-Ren Yao, Zijun Wang, Han Chen, Zhengzhang Liu, Kunpeng Fu, Yanjie Wang, Dongjie Multiagent Systems Artificial Intelligence As cities evolve over time, challenges such as traffic congestion and functional imbalance increasingly necessitate urban renewal through efficient modification of existing plans, rather than complete re-planning. In practice, even minor urban changes require substantial manual effort to redraw geospatial layouts, slowing the iterative planning and decision-making procedure. Motivated by recent advances in agentic systems and multimodal reasoning, we formulate urban renewal as a machine-executable task that iteratively modifies existing urban plans represented in structured geospatial formats. More specifically, we represent urban layouts using GeoJSON and decompose natural-language editing instructions into hierarchical geometric intents spanning polygon-, line-, and point-level operations. To coordinate interdependent edits across spatial elements and abstraction levels, we propose a hierarchical agentic framework that jointly performs multi-level planning and execution with explicit propagation of intermediate spatial constraints. We further introduce an iterative execution-validation mechanism that mitigates error accumulation and enforces global spatial consistency during multi-step editing. Extensive experiments across diverse urban editing scenarios demonstrate significant improvements in efficiency, robustness, correctness, and spatial validity over existing baselines. |
| title | City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2602.19326 |