# Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence

arXiv: https://arxiv.org/abs/2510.16555 · HTML: https://mlsanity.com/paper/2510.16555/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 18 Oct 2025.

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization](https://mlsanity.com/paper/2210.01241/) (2022)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods](https://mlsanity.com/paper/2404.00282/) (2024)
- [Tile2Vec: Unsupervised representation learning for spatially distributed data](https://mlsanity.com/paper/1805.02855/) (2018)
- [Large Language Models are Geographically Biased](https://mlsanity.com/paper/2402.02680/) (2024)
- [UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web](https://mlsanity.com/paper/2310.18340/) (2023)
- [LLMLight: Large Language Models as Traffic Signal Control Agents](https://mlsanity.com/paper/2312.16044/) (2023)
- [Deep Learning the City : Quantifying Urban Perception At A Global Scale](https://mlsanity.com/paper/1608.01769/) (2016)
- [Urban2Vec: Incorporating Street View Imagery and POIs for Multi-Modal Urban Neighborhood Embedding](https://mlsanity.com/paper/2001.11101/) (2020)
- [Towards Vision-Language Geo-Foundation Model: A Survey](https://mlsanity.com/paper/2406.09385/) (2024)
- [Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle](https://mlsanity.com/paper/2509.16679/) (2025)
- [Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models](https://mlsanity.com/paper/2506.14674/) (2025)
- [Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey](https://mlsanity.com/paper/2503.13502/) (2025)
- [Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models](https://mlsanity.com/paper/2402.01749/) (2024)
- [UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding](https://mlsanity.com/paper/2506.23219/) (2025)
- [Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems](https://mlsanity.com/paper/2508.02344/) (2025)
- [Learning Economic Indicators by Aggregating Multi-Level Geospatial Information](https://mlsanity.com/paper/2205.01472/) (2022)

## Built on by (most cited first, 3 of 3)

- [Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling](https://mlsanity.com/paper/2607.13558/) (2026)
- [CoST: Semantic-Aware Urban Understanding via Spatial-Temporal Alignment](https://mlsanity.com/paper/2608.21041/) (2026)
- [LifePlanner: Evaluating LLM Agents for Geo-spatial Planning with Social Media Data](https://mlsanity.com/paper/2608.25039/) (2026)

## Abstract (arXiv)

Rapid urbanization intensifies the demand for Urban General Intelligence (UGI), referring to AI systems that can understand and reason about complex urban environments. Recent studies have built urban foundation models using supervised fine-tuning (SFT) of LLMs and MLLMs, yet these models exhibit persistent geospatial bias, producing regionally skewed predictions and limited generalization. To this end, we propose Urban-R1, a reinforcement learning-based post-training framework that aligns MLLMs with the objectives of UGI. Urban-R1 adopts Group Relative Policy Optimization (GRPO) to optimize reasoning across geographic groups and employs urban region profiling as a proxy task to provide measurable rewards from multimodal urban data. Extensive experiments across diverse regions and tasks show that Urban-R1 effectively mitigates geo-bias and improves cross-region generalization, outperforming both SFT-trained and closed-source models. Our results highlight reinforcement learning alignment as a promising pathway toward equitable and trustworthy urban intelligence.