Reproduce “Learning Better Reasoning for Generative Recommendation with Semantic IDs” 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
Mengdan Zhu, Yufan Zhao, Sophie Di, Yao Zhao, Tao Di, Yulan Yan, Sridhar Iyer, Liang Zhao
Evo-Rec improves next-item recommendation by selecting reasoning traces that increase prediction of the known target, then training with rank-sensitive rewards on catalog-valid Semantic IDs. Across three Amazon Review categories, it outperforms reported baselines in full-catalog ranking; on Games, Recall@5 reaches 0.0847 and NDCG@10 0.0746. Results are offline benchmarks, not deployment evidence.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.