{"slug": "trajgenagent-a-hierarchical-llm-agent-for-human-mobility-trajectory-generation", "title": "TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation", "summary": "TrajGenAgent, a hierarchical LLM-agent framework developed by researchers, generates realistic human mobility trajectories without model fine-tuning by using a two-stage orchestrator-worker design that synthesizes activity chains and grounds them into complete visits. The framework outperforms existing neural and LLM-based baselines in spatiotemporal fidelity, semantic coherence, and behavioral realism on benchmark and large-scale simulation datasets. This approach addresses the high cost and privacy constraints of collecting real trajectory data for applications in transportation, urban planning, and epidemic control.", "body_md": "arXiv:2606.12657v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/trajgenagent-a-hierarchical-llm-agent-for-human-mobility-trajectory-generation", "canonical_source": "https://arxiv.org/abs/2606.12657", "published_at": "2026-06-12 04:00:00+00:00", "updated_at": "2026-06-12 04:51:51.723624+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "generative-ai", "ai-agents"], "entities": ["TrajGenAgent"], "alternates": {"html": "https://wpnews.pro/news/trajgenagent-a-hierarchical-llm-agent-for-human-mobility-trajectory-generation", "markdown": "https://wpnews.pro/news/trajgenagent-a-hierarchical-llm-agent-for-human-mobility-trajectory-generation.md", "text": "https://wpnews.pro/news/trajgenagent-a-hierarchical-llm-agent-for-human-mobility-trajectory-generation.txt", "jsonld": "https://wpnews.pro/news/trajgenagent-a-hierarchical-llm-agent-for-human-mobility-trajectory-generation.jsonld"}}