TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation
Quick Answer
TrajGenAgent is a hierarchical LLM framework for generating human mobility trajectories without fine-tuning, enhancing spatiotemporal fidelity and semantic coherence.
Quick Take
It utilizes a two-stage orchestrator-worker design for activity synthesis and personalized location selection, outperforming existing models in realism while avoiding parameter updates. Evaluation shows significant improvements in behavioral and semantic plausibility over neural and baselines.
Key Points
- TrajGenAgent generates synthetic trajectories without model fine-tuning.
- It employs a two-stage orchestrator-worker design for activity generation.
- The framework enhances spatiotemporal fidelity and semantic coherence.
- Evaluation uses anomaly detection to assess behavioral and semantic plausibility.
- Experiments show significant performance improvements over existing models.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Comments: | 14 pages, 2 figures, 8 tables. Accepted by the 27th IEEE International Conference on Mobile Data Management (MDM 2026) |
| Subjects: | Artificial Intelligence (cs.AI); Databases (cs.DB); Robotics (cs.RO) |
| Cite as: | arXiv:2606.12657 [cs.AI] |
| (or arXiv:2606.12657v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.12657 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Siyu Li [view email]
[v1]
Wed, 10 Jun 2026 20:32:52 UTC (3,329 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.