Reproduce “HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based 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

Zhen Tao, Xun Zhou, Xuhui Chen, Ziyue Qiao, Qingqiang Sun

HARP adds aligned user and item profiles to LLM-based recommendation and uses their compatibility to reweight collaborative neighbors before reranking. Its framework also includes a profile update from warmup successes and misses. On Yelp, it reports Hit@1 of 0.6041 versus MemRec’s 0.487; evidence is from a fixed candidate pool, and code documents item profiles only for Yelp.

Summary by alphaXiv.

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