A four-agent LLM pipeline (user understanding, natural language inference, context summarization, and ranking) improves retrieval-augmented product recommendations on Amazon data by up to 42% in NDCG@5 over recency and vanilla-RAG baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation
A four-agent LLM pipeline (user understanding, natural language inference, context summarization, and ranking) improves retrieval-augmented product recommendations on Amazon data by up to 42% in NDCG@5 over recency and vanilla-RAG baselines.