# CityRiSE: Reasoning Urban Socio-Economic Status in Large Vision-Language Models via Reinforcement Learning

arXiv: https://arxiv.org/abs/2510.22282 · HTML: https://mlsanity.com/paper/2510.22282/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 25 Oct 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 19 of 19)

- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning](https://mlsanity.com/paper/2503.07365/) (2025)
- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [Teaching CLIP to Count to Ten](https://mlsanity.com/paper/2302.12066/) (2023)
- [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025)
- [Large Language Models are Geographically Biased](https://mlsanity.com/paper/2402.02680/) (2024)
- [Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning](https://mlsanity.com/paper/2505.14677/) (2025)
- [VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank](https://mlsanity.com/paper/2505.14460/) (2025)
- [Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward](https://mlsanity.com/paper/2506.07218/) (2025)
- [MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources](https://mlsanity.com/paper/2509.21268/) (2025)
- [Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs](https://mlsanity.com/paper/2506.21656/) (2025)
- [Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models](https://mlsanity.com/paper/2506.14674/) (2025)
- [CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing](https://mlsanity.com/paper/2506.00530/) (2025)
- [UrbanFeel: A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspective](https://mlsanity.com/paper/2509.22228/) (2025)
- [Harnessing the Synergy between LLM Agents and Knowledge Graphs for Urban Socioeconomic Prediction](https://mlsanity.com/paper/2411.00028/) (2024)
- [What can LLM tell us about cities?](https://mlsanity.com/paper/2411.16791/) (2024)
- [GeoSEE: Regional Socio-Economic Estimation With a Large Language Model](https://mlsanity.com/paper/2406.09799/) (2024)

## Abstract (arXiv)

Urban socio-economic sensing plays a vital role in advancing global sustainable development goals. With the advent of Large Vision-Language Models (LVLMs), new opportunities have emerged to address this challenge by framing it as a multi-modal perception and reasoning task. However, recent studies show that LVLMs still struggle to make accurate and interpretable socio-economic predictions from visual data. To overcome these limitations and fully exploit the potential of LVLMs, we propose CityRiSE, a novel framework for Reasoning urban Socio-Economic status in LVLMs via reinforcement learning (RL). With carefully curated multi-modal dataset and verifiable reward design, our approach guides the LVLM to focus on semantically meaningful visual cues, enabling structured and goal-oriented reasoning for generalist socio-economic status prediction. Experiments demonstrate that CityRiSE, equipped with emergent reasoning, significantly outperforms existing baselines, improving both prediction accuracy and generalization across diverse urban contexts, especially on unseen cities and unseen indicators. This work highlights the promise of combining RL and LVLMs for interpretable and generalist urban socio-economic sensing.