Skip to content
AI Atlas
PaperActive

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

arxiv.org/abs/2602.19326

Updated 32 min ago · first seen 11 Sept 2026

paper_01M294GPVV4QJPB0PJZ8XH1Y13

Published
11 Sept 2026
T1 · 32 min ago
arXiv
2602.19326
T1 · 32 min ago
Category
cs.MA
T1 · 32 min ago

Abstract

-cross Abstract: 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.

Authors 9

Rui Liu, Steven Jige Quan, Zhong-Ren Peng, Zijun Yao, Han Wang, Pengyang Wang, Kunpeng Liu, Yanjie Fu, Dongjie Wang

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 32 min agohigh

Arxiv announce type
replace

Source:arXiv (Atom API + RSS)T1observed 32 min agohigh

arXiv id
2602.19326

Source:arXiv (Atom API + RSS)T1observed 32 min agohigh

Categories
cs.MA, cs.AI

Source:arXiv (Atom API + RSS)T1observed 32 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 32 min agohigh

Primary category
cs.MA

Source:arXiv (Atom API + RSS)T1observed 32 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 32 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

32 min ago

Conflicts

None