# From Narrative to Action: A Hierarchical LLM-Agent Framework for Human Mobility Generation

arXiv: https://arxiv.org/abs/2510.24802 · HTML: https://mlsanity.com/paper/2510.24802/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 45 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 16 of 16)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation](https://mlsanity.com/paper/2402.14744/) (2024)
- [A Survey on Deep Learning for Human Mobility](https://mlsanity.com/paper/2012.02825/) (2020)
- [Narrative Planning: Balancing Plot and Character](https://mlsanity.com/paper/1401.3841/) (2014)
- [Generative Adversarial Networks for Spatio-temporal Data: A Survey](https://mlsanity.com/paper/2008.08903/) (2020)
- [Be More Real: Travel Diary Generation Using LLM Agents and Individual Profiles](https://mlsanity.com/paper/2407.18932/) (2024)
- [TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation](https://mlsanity.com/paper/2502.18712/) (2025)
- [Chain-of-Planned-Behaviour Workflow Elicits Few-Shot Mobility Generation in LLMs](https://mlsanity.com/paper/2402.09836/) (2024)
- [Generative Models for Simulating Mobility Trajectories](https://mlsanity.com/paper/1811.12801/) (2018)
- [Deep Activity Model: A Generative Approach for Human Mobility Pattern Synthesis](https://mlsanity.com/paper/2405.17468/) (2024)
- [Generating synthetic mobility data for a realistic population with RNNs to improve utility and privacy](https://mlsanity.com/paper/2201.01139/) (2022)
- [Privacy in trajectory micro-data publishing : a survey](https://mlsanity.com/paper/1903.12211/) (2019)
- [Identifying latent activity behaviors and lifestyles using mobility data to describe urban dynamics](https://mlsanity.com/paper/2209.12095/) (2022)
- [Urban Analytics: History, Trajectory, and Critique](https://mlsanity.com/paper/2105.07020/) (2021)

## Built on by (most cited first, 1 of 1)

- [Towards Efficient and Evidence-grounded Mobility Prediction with LLM-Driven Agent](https://mlsanity.com/paper/2606.05130/) (2026)

## Abstract (arXiv)

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 convert narratives into machine-readable plans. A dynamic execution module further grounds agents in geographic environments and enables adaptive behavioral adjustments guided by a novel occupation-aware metric, Mobility Entropy by Occupation (MEO), which captures heterogeneous schedule flexibility across different occupational personalities. At the micro level, the agent executes concrete actions-selecting locations, transportation modes, and time intervals-through interaction with an environmental simulation. By embedding this multi-layer cognitive process, the framework produces not only synthetic trajectories that align closely with real-world patterns but also interpretable representations of human decision logic. This research advances synthetic mobility generation from a data-driven paradigm to a cognition-driven simulation, providing a scalable pathway for understanding, predicting, and synthesizing complex urban mobility behaviors through hierarchical LLM agents.