City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification
🤖 AI Summary
This work addresses the inefficiency in urban renewal planning caused by the labor-intensive redrawing of geographic layouts for minor modifications, which hinders rapid design iteration. To overcome this limitation, the paper formulates urban renewal as an executable task grounded in structured GeoJSON representations and introduces a hierarchical agent architecture. This framework interprets natural language instructions to generate multi-level geometric operations, while an iterative execution–verification loop explicitly propagates spatial constraints across abstraction layers to ensure global consistency. By integrating multimodal reasoning with geometric intent parsing, the proposed method substantially improves efficiency, robustness, correctness, and spatial validity across diverse editing scenarios, outperforming existing baselines.
Application Category
📝 Abstract
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.
Problem
Research questions and friction points this paper is trying to address.
urban renewal
geospatial modification
dependency-aware editing
structured urban plans
spatial consistency
Innovation
Methods, ideas, or system contributions that make the work stand out.
hierarchical agentic execution
dependency-aware editing
geospatial modification
structured urban planning
iterative validation
🔎 Similar Papers
No similar papers found.
