# Cognitive-Aligned Spatio-Temporal Large Language Models For Next Point-of-Interest Prediction

arXiv: https://arxiv.org/abs/2510.14702 · HTML: https://mlsanity.com/paper/2510.14702/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [Multi-Interest Network with Dynamic Routing for Recommendation at Tmall](https://mlsanity.com/paper/1904.08030/) (2019)
- [Learnable Item Tokenization for Generative Recommendation](https://mlsanity.com/paper/2405.07314/) (2024)
- [STAN: Spatio-Temporal Attention Network for Next Location Recommendation](https://mlsanity.com/paper/2102.04095/) (2021)
- [Generative Recommender with End-to-End Learnable Item Tokenization](https://mlsanity.com/paper/2409.05546/) (2024)
- [Large Scale Product Graph Construction for Recommendation in E-commerce](https://mlsanity.com/paper/2010.05525/) (2020)
- [Aligning Large Language Models with Recommendation Knowledge](https://mlsanity.com/paper/2404.00245/) (2024)
- [AANG: Automating Auxiliary Learning](https://mlsanity.com/paper/2205.14082/) (2022)
- [A Survey of Point-of-interest Recommendation in Location-based Social Networks](https://mlsanity.com/paper/1607.00647/) (2016)
- [Universal Item Tokenization for Transferable Generative Recommendation](https://mlsanity.com/paper/2504.04405/) (2025)
- [Context-based Fast Recommendation Strategy for Long User Behavior Sequence in Meituan Waimai](https://mlsanity.com/paper/2403.12566/) (2024)
- [Difference-Masking: Choosing What to Mask in Continued Pretraining](https://mlsanity.com/paper/2305.14577/) (2023)
- [A Simple Contrastive Framework Of Item Tokenization For Generative Recommendation](https://mlsanity.com/paper/2506.16683/) (2025)

## Built on by (most cited first, 2 of 2)

- [Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation](https://mlsanity.com/paper/2601.04562/) (2026)
- [Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation](https://mlsanity.com/paper/2605.11807/) (2026)

## Abstract (arXiv)

The next point-of-interest (POI) recommendation task aims to predict the users' immediate next destinations based on their preferences and historical check-ins, holding significant value in location-based services. Recently, large language models (LLMs) have shown great potential in recommender systems, which treat the next POI prediction in a generative manner. However, these LLMs, pretrained primarily on vast corpora of unstructured text, lack the native understanding of structured geographical entities and sequential mobility patterns required for next POI prediction tasks. Moreover, in industrial-scale POI prediction applications, incorporating world knowledge and alignment of human cognition, such as seasons, weather conditions, holidays, and users' profiles (such as habits, occupation, and preferences), can enhance the user experience while improving recommendation performance. To address these issues, we propose CoAST (Cognitive-Aligned Spatial-Temporal LLMs), a framework employing natural language as an interface, allowing for the incorporation of world knowledge, spatio-temporal trajectory patterns, profiles, and situational information. Specifically, CoAST mainly comprises of 2 stages: (1) Recommendation Knowledge Acquisition through continued pretraining on the enriched spatial-temporal trajectory data of the desensitized users; (2) Cognitive Alignment to align cognitive judgments with human preferences using enriched training data through Supervised Fine-Tuning (SFT) and a subsequent Reinforcement Learning (RL) phase. Extensive offline experiments on various real-world datasets and online experiments deployed in "Guess Where You Go" of AMAP App homepage demonstrate the effectiveness of CoAST.