TravelAgent: Generative Agents in the Built Environment

2024-12-25

AI Summary

Traditional urban spatial simulation struggles to capture the complexity and dynamism of human behavior. Method: This study proposes the first large language model (LLM)-driven generative agent simulation framework, enabling embodied, context-adaptive, and interpretable behavioral modeling of LLM agents within 3D built environments. It integrates multimodal perception encoding, spatial semantic parsing, and emotion–language joint analysis to support human-like behaviors—including navigation, pathfinding, and open-ended exploration. Contribution/Results: In 100 simulation runs (1,898 agent steps), task completion reached 76%. Tripartite analysis uncovered perceptual biases in environmental interpretation, evolutionary patterns in adaptive strategies, and persistent behavioral bottlenecks. The framework establishes a novel paradigm and empirically verifiable tool for urban design optimization and spatial cognition research.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

Understanding human behavior in built environments is critical for designing functional, user centered urban spaces. Traditional approaches, such as manual observations, surveys, and simplified simulations, often fail to capture the complexity and dynamics of real world behavior. To address these limitations, we introduce TravelAgent, a novel simulation platform that models pedestrian navigation and activity patterns across diverse indoor and outdoor environments under varying contextual and environmental conditions. TravelAgent leverages generative agents integrated into 3D virtual environments, enabling agents to process multimodal sensory inputs and exhibit human-like decision-making, behavior, and adaptation. Through experiments, including navigation, wayfinding, and free exploration, we analyze data from 100 simulations comprising 1898 agent steps across diverse spatial layouts and agent archetypes, achieving an overall task completion rate of 76%. Using spatial, linguistic, and sentiment analyses, we show how agents perceive, adapt to, or struggle with their surroundings and assigned tasks. Our findings highlight the potential of TravelAgent as a tool for urban design, spatial cognition research, and agent-based modeling. We discuss key challenges and opportunities in deploying generative agents for the evaluation and refinement of spatial designs, proposing TravelAgent as a new paradigm for simulating and understanding human experiences in built environments.

Problem

• Behavioral Simulation
• Urban Design
• User-Centered Architecture

Innovation

• TravelAgent
• 3D virtual environment
• spatial design evaluation