REVIEW 9 cited by
Chain-of-Planned-Behaviour Workflow Elicits Few-Shot Mobility Generation in LLMs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The powerful reasoning capabilities of large language models (LLMs) have brought revolutionary changes to many fields, but their performance in human behaviour generation has not yet been extensively explored. This gap likely emerges because the internal processes governing behavioral intentions cannot be solely explained by abstract reasoning. Instead, they are also influenced by a multitude of factors, including social norms and personal preference. Inspired by the Theory of Planned Behaviour (TPB), we develop a LLM workflow named Chain-of-Planned Behaviour (CoPB) for mobility behaviour generation, which reflects the important spatio-temporal dynamics of human activities. Through exploiting the cognitive structures of attitude, subjective norms, and perceived behaviour control in TPB, CoPB significantly enhance the ability of LLMs to reason the intention of next movement. Specifically, CoPB substantially reduces the error rate of mobility intention generation from 57.8% to 19.4%. To improve the scalability of the proposed CoPB workflow, we further explore the synergy between LLMs and mechanistic models. We find mechanistic mobility models, such as gravity model, can effectively map mobility intentions to physical mobility behaviours. The strategy of integrating CoPB with gravity model can reduce the token cost by 97.7% and achieve better performance simultaneously. Besides, the proposed CoPB workflow can facilitate GPT-4-turbo to automatically generate high quality labels for mobility behavior reasoning. We show such labels can be leveraged to fine-tune the smaller-scale, open source LLaMA 3-8B, which significantly reduces usage costs without sacrificing the quality of the generated behaviours.
Forward citations
Cited by 9 Pith papers
-
CrimeMind: Simulating Urban Crime with Multi-Modal LLM Agents
An LLM-driven agent-based model that integrates Routine Activity Theory and street-view safety perception outperforms baselines in simulating urban crime hotspots across four U.S. cities.
-
AgentSociety 2: An Integrated Research Environment for Executable Social Science
An integrated LLM-agent environment runs social-science experiments from hypothesis to manuscript, reproducing several known human patterns while failing on others (implicit self-bias, free-riding decay, norm collapse).
-
Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation
A latent-space reasoning cache with a lightweight decoder cuts the cost of LLM-based human mobility simulation by roughly 40-90% while keeping trajectory quality comparable.
-
Bridging Individual and Collective Realism in LLM-Based Human Mobility Simulation via Mobility Scaling-Law Guidance
M2LSimu uses population-level mobility statistics as a reward signal to iteratively adjust LLM prompts, improving simulated trajectories' match to real mobility patterns.
-
Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning
CORE embeds trajectories by letting an LLM describe POIs around roads, encoding each road-segment choice with a mixture-of-experts, and outperforming 12 prior TRL methods on six urban tasks.
-
Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models
The monotonicity of token probabilities during initial decoding predicts chain-of-thought gains, enabling dynamic selection between CoT and direct answers.
-
Involution game with migration and spatial heterogeneity of social resources
Equal regional resources suppress involution while resource disparity and higher total resources promote it; migration probability barely changes the evolutionary outcome.
-
Large language model as user daily behavior data generator: balancing population diversity and individual personality
LLM-generated synthetic behavior data improves mobility and smartphone-use prediction models by up to 18.9% and captures roughly 60 to 88% of the gains from real-data fine-tuning.
-
Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications
The paper defines urban LLM agents, surveys their sensing, memory, reasoning, execution, and learning workflows, and organizes their applications across planning, transportation, environment, safety, and society.
Discussion (0). Sign in to comment.