Reimagining Urban Science: Scaling Causal Inference with Large Language Models

2025-04-15

AI Summary

Urban causal research faces structural bottlenecks including inefficient causal hypothesis generation, challenges in integrating heterogeneous multi-source data, and fragile experimental methodologies. To address these, we propose AutoUrbanCI, an LLM-driven automated causal inference framework featuring a novel four-module UrbanCI agent architecture—uniquely integrating multimodal data engineering, causal inference, policy semantic modeling, and multi-agent coordination. AutoUrbanCI enables an end-to-end closed-loop workflow spanning causal hypothesis generation, interpretable validation, and actionable policy recommendation. We introduce a rigor–transparency–balanced evaluation criterion for causal analysis and establish a new AI-augmented human–machine collaboration paradigm. Empirical results demonstrate significant improvements in reproducibility, cross-disciplinary accessibility, and policy inclusivity of urban causal analysis.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Urban causal research is essential for understanding the complex dynamics of cities and informing evidence-based policies. However, it is challenged by the inefficiency and bias of hypothesis generation, barriers to multimodal data complexity, and the methodological fragility of causal experimentation. Recent advances in large language models (LLMs) present an opportunity to rethink how urban causal analysis is conducted. This Perspective examines current urban causal research by analyzing taxonomies that categorize research topics, data sources, and methodological approaches to identify structural gaps. We then introduce an LLM-driven conceptual framework, AutoUrbanCI, composed of four distinct modular agents responsible for hypothesis generation, data engineering, experiment design and execution, and results interpretation with policy recommendations. We propose evaluation criteria for rigor and transparency and reflect on implications for human-AI collaboration, equity, and accountability. We call for a new research agenda that embraces AI-augmented workflows not as replacements for human expertise but as tools to broaden participation, improve reproducibility, and unlock more inclusive forms of urban causal reasoning.

Problem

• Address inefficiency and bias in urban hypothesis generation
• Overcome barriers in multimodal urban data complexity
• Improve methodological fragility in urban causal experimentation

Innovation

• LLM-driven modular framework AutoUrbanCI
• Agents for hypothesis and data handling
• Evaluation for rigor and transparency