aiqbench analysis
TrajGenAgent introduces a hierarchical LLM-agent framework that generates realistic human mobility trajectories without requiring model fine-tuning, addressing the trade-off between reasoning capabilities and computational cost in synthetic data creation. By combining semantic activity synthesis with deterministic workflows for spatiotemporal grounding, this approach offers improved fidelity over existing baselines while maintaining zero-shot generalization. The work advances AI applications in urban planning and transportation by providing a scalable method to create privacy-preserving mobility datasets using large language models.
TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation
arXiv:2606.12657v1 Announce Type: new 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.
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.
14 pages, 2 figures, 8 tables. Accepted by the 27th IEEE International Conference on Mobile Data Management (MDM 2026)
Artificial Intelligence (cs.AI); Databases (cs.DB); Robotics (cs.RO)
arXiv:2606.12657 [cs.AI]
(or arXiv:2606.12657v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.12657 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 294 words
Related coverage
Gemini 4 Argon for Robotics
Google DeepMind · Oct 13, 2026
An overview of frontier AI company monitoring practices in mid 2026
LessWrong · Oct 7, 2026
[AINews] not much happened today
Latent Space · Sep 10, 2026
[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026