REVIEW 11 cited by
Urban Generative Intelligence (UGI): A Foundational Platform for Agents in Embodied City Environment
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Urban environments, characterized by their complex, multi-layered networks encompassing physical, social, economic, and environmental dimensions, face significant challenges in the face of rapid urbanization. These challenges, ranging from traffic congestion and pollution to social inequality, call for advanced technological interventions. Recent developments in big data, artificial intelligence, urban computing, and digital twins have laid the groundwork for sophisticated city modeling and simulation. However, a gap persists between these technological capabilities and their practical implementation in addressing urban challenges in an systemic-intelligent way. This paper proposes Urban Generative Intelligence (UGI), a novel foundational platform integrating Large Language Models (LLMs) into urban systems to foster a new paradigm of urban intelligence. UGI leverages CityGPT, a foundation model trained on city-specific multi-source data, to create embodied agents for various urban tasks. These agents, operating within a textual urban environment emulated by city simulator and urban knowledge graph, interact through a natural language interface, offering an open platform for diverse intelligent and embodied agent development. This platform not only addresses specific urban issues but also simulates complex urban systems, providing a multidisciplinary approach to understand and manage urban complexity. This work signifies a transformative step in city science and urban intelligence, harnessing the power of LLMs to unravel and address the intricate dynamics of urban systems. The code repository with demonstrations will soon be released here https://github.com/tsinghua-fib-lab/UGI.
Forward citations
Cited by 11 Pith papers
-
UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding
A fine-tuned small multimodal LLM outperforms much larger general models on urban tasks in a new benchmark, with caveats about benchmark overlap with training data.
-
Modeling Earth-Scale Human-Like Societies with One Billion Agents
Light Society scales LLM-agent social simulations to one billion agents by substituting most LLM interactions with a distilled surrogate model.
-
Generative AI as a Playful yet Offensive Tourist: Exploring Tensions Between Playful Features and Citizen Concerns in Designing Urban Play
A qualitative study identifies six playful and five concerning qualities of generative-AI urban play, based on workshops with 14 designers and 14 citizens using an image-to-image tool.
-
BIGCity: A Universal Spatiotemporal Model for Unified Trajectory and Traffic State Data Analysis
One model, BIGCity, represents both individual trajectories and population-level traffic states as sequences of shared ST-units and performs eight spatiotemporal tasks with a single set of weights, reportedly beating ...
-
UniFlow: A Foundation Model for Unified Urban Spatio-Temporal Flow Prediction
UniFlow unifies grid and graph urban flow prediction in one transformer with learned memory retrieval, but its best-on-all-datasets claim is contradicted by its own TrafficNJ result.
-
CityLLM: A framework for natural-language querying of semantic 3D city models
CityLLM, an LLM agent over PostGIS and Neo4j, answers 85–100% of 54 curated Rotterdam city-model queries correctly.
-
LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation
A multimodal LLM framework generates interactive Unreal-based 3D environments from text and height maps, claiming superior layout accuracy and over 90x faster production than manual methods.
-
SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber World
SmartAgent is a GUI agent that adds user-preference reasoning through three thought steps, but its intermediate 'underlying requirement' step does not improve item recommendation over end-to-end training.
-
Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications
The paper defines urban LLM agents, surveys their sensing, memory, reasoning, execution, and learning workflows, and organizes their applications across planning, transportation, environment, safety, and society.
-
A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
This survey organizes recent LLM-based multi-agent research into task-solving, simulation, and agent-evaluation applications, and identifies efficiency and evaluation gaps as key open problems.
-
A Survey on Agent Workflow -- Status and Future
A review that classifies 24 agent workflow systems along functional and architectural axes and argues for standardization, optimization, and security work.
Discussion (0). Continue with ORCID to comment.