LLM agents and spatial KGs evaluate neighborhood livability

Researchers have developed a novel framework that integrates spatial knowledge graphs (KGs) with large language models (LLMs) to evaluate neighborhood livability. This system generates and refines household schedules by using a spatial KG to retrieve contextual information and LLMs to create structured schedules. The framework then uses GIS-based network analysis to derive travel paths and times, enabling synthetic interviews with simulated residents to assess daily convenience and accessibility burdens. A prototype demonstration in Shenzhen highlighted that nominal facility availability does not guarantee convenient access for residents with mobility limitations or care responsibilities. AI

IMPACT This framework offers a novel approach to understanding resident experience in urban planning by simulating daily life and accessibility.

RANK_REASON The cluster contains an academic paper detailing a new framework and methodology. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.MA (Multiagent) →

• geographic information system
• Graph RAG
• Large Language Models
• Shenzhen
• Spatial Knowledge Graph

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →