TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation

Computer Science > Artificial Intelligence [Submitted on 10 Jun 2026] TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation Siyu Li, Toan Tran, Lingyi Zhao, Khurram Shafique, Li Xiong 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 Focus to learn more Submission history From: Siyu Li [view email] [v1] Wed, 10 Jun 2026 20:32:52 UTC (3,329 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.DB cs.RO References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)