# Human Mobility Modeling with Household Coordination Activities under Limited Information via Retrieval-Augmented LLMs

arXiv: https://arxiv.org/abs/2409.17495 · HTML: https://mlsanity.com/paper/2409.17495/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in RAG for recommendation, one of 15 directions in Retrieval-augmented generation.
- Builds on 13 of its 49 references that are in the map.
- First posted on arXiv 26 Sep 2024.

## Placed in

- Retrieval-augmented generation / [RAG for recommendation](https://mlsanity.com/rag/rag-for-recommendation/)

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [VirtualHome: Simulating Household Activities via Programs](https://mlsanity.com/paper/1806.07011/) (2018)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [GPT-Driver: Learning to Drive with GPT](https://mlsanity.com/paper/2310.01415/) (2023)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [A Survey on Deep Learning for Human Mobility](https://mlsanity.com/paper/2012.02825/) (2020)
- [Improving Language Models via Plug-and-Play Retrieval Feedback](https://mlsanity.com/paper/2305.14002/) (2023)
- [Semantic Trajectory Data Mining with LLM-Informed POI Classification](https://mlsanity.com/paper/2405.11715/) (2024)
- [Deep Activity Model: A Generative Approach for Human Mobility Pattern Synthesis](https://mlsanity.com/paper/2405.17468/) (2024)
- [Exploring Human Mobility for Multi-Pattern Passenger Prediction: A Graph Learning Framework](https://mlsanity.com/paper/2202.10339/) (2022)

## Built on by (most cited first, 7 of 7)

- [Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework](https://mlsanity.com/paper/2412.06681/) (2024)
- [RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility](https://mlsanity.com/paper/2509.23115/) (2025)
- [Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation](https://mlsanity.com/paper/2602.16727/) (2026)
- [ActivityEditor: Learning to Synthesize Physically Valid Human Mobility](https://mlsanity.com/paper/2604.05529/) (2026)
- [PEMAND: Persona-Enriched Multi-Agent Negotiation for Household Decision-Making](https://mlsanity.com/paper/2604.10475/) (2026)
- [GPS-Enhanced Tourist Mobility Modeling with Seasonal Spatial Priors and LLM-Based Activity Chain Generation](https://mlsanity.com/paper/2605.29578/) (2026)
- [Encounter-Driven City-Scale Human Mobility Generation with Large Language Models](https://mlsanity.com/paper/2610.17672/) (2026)

## Abstract (arXiv)

Understanding human mobility patterns has long been a challenging task in transportation modeling. Due to the difficulties in obtaining high-quality training datasets across diverse locations, conventional activity-based models and learning-based human mobility modeling algorithms are particularly limited by the availability and quality of datasets. Current approaches primarily focus on spatial-temporal patterns while neglecting semantic relationships such as logical connections or dependencies between activities and household coordination activities like joint shopping trips or family meal times, both crucial for realistic mobility modeling. We propose a retrieval-augmented large language model (LLM) framework that generates activity chains with household coordination using only public accessible statistical and socio-demographic information, reducing the need for sophisticated mobility data. The retrieval-augmentation mechanism enables household coordination and maintains statistical consistency across generated patterns, addressing a key gap in existing methods. Our validation with NHTS and SCAG-ABM datasets demonstrates effective mobility synthesis and strong adaptability for regions with limited mobility data availability.