# CityLLM: A framework for natural-language querying of semantic 3D city models

arXiv: https://arxiv.org/abs/2607.14542 · HTML: https://mlsanity.com/paper/2607.14542/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 17 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 2 of 2)

- [Urban Generative Intelligence (UGI): A Foundational Platform for Agents in Embodied City Environment](https://mlsanity.com/paper/2312.11813/) (2023)
- [Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models](https://mlsanity.com/paper/2402.01749/) (2024)

## Abstract (arXiv)

Semantic 3D city models provide rich geometric and semantic information, but remain challenging for non-experts and interdisciplinary researchers to access and query due to their complex structures and specialized data formats. To address this issue, we present CityLLM, a framework for natural-language querying of semantic 3D city models alongside complementary urban datasets. The framework combines spatial and graph databases within an LLM-based workflow that supports iterative query refinement and cross-database chaining. We evaluate CityLLM on a CityJSON dataset of Rotterdam (853 LoD2 buildings) using GPT-OSS, Gemini 3.1, and GPT-5.4, along with selected variants, across multiple metrics: answer correctness, visualization correctness, query success, and retry attempts. A total of 54 natural-language queries are curated across four scenarios: spatial, graph, cross-database, and conversational. Results show strong overall performance, with answer correctness ranging from 85.2% to 100%, visualization correctness from 92.9% to 100%, a 100% query success rate, and fewer than three retries across all 54 queries. Overall, the findings suggest that CityLLM provides a lightweight and extensible approach for conversational access to semantic 3D city data.