TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation

2026-06-10

AI Summary

Real human mobility trajectory data are constrained by high collection costs and privacy concerns, necessitating high-fidelity synthetic generation methods. This work proposes a fine-tuning-free, hierarchical large language model (LLM) agent framework that leverages a two-stage orchestrator-worker architecture to generate personalized, spatiotemporally consistent, and semantically plausible trajectories. The approach integrates key components including personalized point-of-interest (POI) retrieval, distance-aware location selection, kinematics-driven temporal propagation, and LLM-based duration estimation, orchestrated through in-context learning and deterministic workflows. Evaluated on multiple benchmarks and large-scale simulated datasets, the method significantly outperforms existing neural network and LLM baselines, achieving notable advances in spatiotemporal fidelity, semantic coherence, and individual behavioral realism.

Abstract

Human mobility data is important for transportation, urban planning, and epidemic control, but large-scale trajectory collection is often costly and privacy-constrained, motivating realistic synthetic trajectory generation. Existing LLM-based generators typically rely on either prompt engineering, which preserves zero-shot reasoning but lacks fine-grained spatiotemporal grounding, or trajectory-level fine-tuning, which improves statistical precision but incurs substantial computational cost and may weaken general reasoning. We propose TrajGenAgent, a semantic-aware hierarchical LLM-agent framework for human mobility trajectory generation without model fine-tuning. TrajGenAgent uses a two-stage orchestrator-worker design: an LLM first synthesizes an individual- and weekday-conditioned activity chain from historical evidence via in-context learning, and a deterministic workflow then grounds each activity into a complete visit using personalized POI retrieval, distance-aware location selection, kinematics-aware travel-time propagation, and LLM-based duration estimation. To evaluate realism beyond aggregate spatiotemporal statistics, we introduce an anomaly-detection-based evaluation framework using two complementary detectors to assess behavioral and semantic plausibility. Experiments on benchmark and large-scale simulation datasets show that TrajGenAgent improves spatiotemporal fidelity, semantic coherence, and individual-specific behavioral realism over representative neural and LLM-based baselines, while avoiding parameter updates.

Problem

• human mobility
• trajectory generation
• synthetic data
• privacy-preserving
• spatiotemporal realism

Innovation

• hierarchical LLM agent
• human mobility trajectory generation
• in-context learning
• spatiotemporal grounding
• anomaly-detection-based evaluation