From Narrative to Action: A Hierarchical LLM-Agent Framework for Human Mobility Generation
Qiumeng Li, Chunhou Ji, Xinyue Liu

TL;DR
This paper introduces a hierarchical LLM-agent framework that models human mobility by integrating narrative reasoning, planning, and execution, resulting in more realistic and interpretable synthetic trajectories.
Contribution
It presents a novel multi-layer cognitive hierarchy combining narrative generation, structured planning, and adaptive execution within LLMs for human mobility simulation.
Findings
Generated trajectories closely match real-world mobility patterns
The framework produces interpretable human decision logic
Adaptive behavior guided by occupation-aware mobility entropy
Abstract
Understanding and replicating human mobility requires not only spatial-temporal accuracy but also an awareness of the cognitive hierarchy underlying real-world travel decisions. Traditional agent-based or deep learning models can reproduce statistical patterns of movement but fail to capture the semantic coherence and causal logic of human behavior. Large language models (LLMs) show potential, but struggle to balance creative reasoning with strict structural compliance. This study proposes a Hierarchical LLM-Agent Framework, termed Narrative-to-Action, that integrates high-level narrative reasoning, mid-level reflective planning, and low-level behavioral execution within a unified cognitive hierarchy. At the macro level, one agent is employed as a "creative writer" to produce diary-style narratives rich in motivation and context, then uses another agent as a "structural parser" to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
