From Narrative to Action: A Hierarchical LLM-Agent Framework for Human Mobility Generation
- URL: http://arxiv.org/abs/2510.24802v1
- Date: Tue, 28 Oct 2025 00:26:36 GMT
- Title: From Narrative to Action: A Hierarchical LLM-Agent Framework for Human Mobility Generation
- Authors: Qiumeng Li, Chunhou Ji, Xinyue Liu,
- Abstract summary: Large language models (LLMs) show potential, but struggle to balance creative reasoning with strict structural compliance.<n>This study proposes a Hierarchical LLM-Agent Framework that integrates high-level narrative reasoning, mid-level reflective planning.<n>This research advances synthetic mobility generation from a data-driven paradigm to a spatial-driven simulation.
- Score: 3.242664635630543
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- 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 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.
Related papers
- Agentic Reasoning for Large Language Models [122.81018455095999]
Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making.<n>Large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, but struggle in open-ended and dynamic environments.<n>Agentic reasoning marks a paradigm shift by reframing LLMs as autonomous agents that plan, act, and learn through continual interaction.
arXiv Detail & Related papers (2026-01-18T18:58:23Z) - Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs [10.99947795031516]
Large Language Models exhibit implicit personalities in their generation, but reliably controlling or aligning these traits to meet specific needs remains an open challenge.<n>We propose a novel pipeline that extracts hidden state activations from transformer layers using the Big Five Personality Traits.<n>Our findings reveal that personality traits occupy a low-rank shared subspace, and that these latent structures can be transformed into actionable mechanisms for effective steering.
arXiv Detail & Related papers (2025-10-29T05:56:39Z) - Fundamentals of Building Autonomous LLM Agents [64.39018305018904]
This paper reviews the architecture and implementation methods of agents powered by large language models (LLMs)<n>The research aims to explore patterns to develop "agentic" LLMs that can automate complex tasks and bridge the performance gap with human capabilities.
arXiv Detail & Related papers (2025-10-10T10:32:39Z) - Executable Analytic Concepts as the Missing Link Between VLM Insight and Precise Manipulation [70.8381970762877]
Vision-Language Models (VLMs) have demonstrated remarkable capabilities in semantic reasoning and task planning.<n>We introduce GRACE, a novel framework that grounds VLM-based reasoning through executable analytic concepts.<n>G GRACE provides a unified and interpretable interface between high-level instruction understanding and low-level robot control.
arXiv Detail & Related papers (2025-10-09T09:08:33Z) - The Landscape of Agentic Reinforcement Learning for LLMs: A Survey [103.78397717362797]
The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL)<n>This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM-RL with the temporally extended, partially observable Markov decision processes (POMDPs) that define Agentic RL.
arXiv Detail & Related papers (2025-09-02T17:46:26Z) - A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence [87.08051686357206]
Large Language Models (LLMs) have demonstrated strong capabilities but remain fundamentally static.<n>As LLMs are increasingly deployed in open-ended, interactive environments, this static nature has become a critical bottleneck.<n>This survey provides the first systematic and comprehensive review of self-evolving agents.
arXiv Detail & Related papers (2025-07-28T17:59:05Z) - GATSim: Urban Mobility Simulation with Generative Agents [12.893057419094932]
We introduce GATSim, a novel framework to simulate urban mobility using generative agents with rich, human-like behaviors.<n>Unlike conventional approaches, GATSim agents are characterized by diverse socioeconomic profiles, individual lifestyles, and evolving preferences shaped through psychologically informed memory systems.<n>We implement a prototype system and conduct systematic validation, demonstrating that generative agents produce believable and coherent travel behaviors.
arXiv Detail & Related papers (2025-06-29T15:52:16Z) - The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners [1.9417191498842046]
We evaluate the role of agentic sophistication in shaping artificial reasoners' performance.<n>We benchmarked three agent designs: a simple game-theoretic model, an unstructured LLM-as-agent model, and an LLM integrated into a traditional agentic framework.<n>Our analysis, covering over 2000 reasoning samples across 25 agent configurations, shows that human-inspired cognitive structures can enhance LLM agents' alignment with human strategic behaviour.
arXiv Detail & Related papers (2025-05-14T13:51:24Z) - Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoning [69.5875073447454]
This paper advances motion agents empowered by large language models (LLMs) toward autonomous navigation in dynamic and cluttered environments.<n>Our training-free framework supports multi-agent coordination, closed-loop replanning, and dynamic obstacle avoidance without retraining or fine-tuning.
arXiv Detail & Related papers (2025-03-10T13:39:09Z) - TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation [3.8106509573548286]
This work leverages Large Language Models (LLMs) to simulate human mobility, addressing challenges like high costs and privacy concerns in traditional models.<n>Our hierarchical framework integrates persona generation, activity selection, and destination prediction, using real-world demographic and psychological data.
arXiv Detail & Related papers (2025-02-26T00:13:26Z) - Dynamic planning in hierarchical active inference [0.0]
We refer to the ability of the human brain to infer and impose motor trajectories related to cognitive decisions.
This study focuses on the topic of dynamic planning in active inference.
arXiv Detail & Related papers (2024-02-18T17:32:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.