Reproduce “Category-Anchored Large Language Models for Next POI Recommendation” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Lexi Bai, Xiaopeng Zeng, Xun Zhou, Yuanshao Zhu, James Jianqiao Yu

ANCHOR addresses next-place recommendation by separating category intent from exact point-of-interest selection. It uses a language model to predict a likely category, retrieves candidates from category, visit, and preference evidence, then reranks them using history and time context. Across three datasets, it leads Think2Go in metrics, with a 7.56% relative Acc@1 gain on NYC; it remains dependent on mobility history.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.