ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Maragheh, Reza Yousefi, Vadla, Pratheek, Gupta, Priyank, Zhao, Kai, Inan, Aysenur, Yao, Kehui, Xu, Jianpeng, Kanumala, Praveen, Cho, Jason, Kumar, Sushant
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918121950937088
author Maragheh, Reza Yousefi
Vadla, Pratheek
Gupta, Priyank
Zhao, Kai
Inan, Aysenur
Yao, Kehui
Xu, Jianpeng
Kanumala, Praveen
Cho, Jason
Kumar, Sushant
author_facet Maragheh, Reza Yousefi
Vadla, Pratheek
Gupta, Priyank
Zhao, Kai
Inan, Aysenur
Yao, Kehui
Xu, Jianpeng
Kanumala, Praveen
Cho, Jason
Kumar, Sushant
contents Retrieval-Augmented Generation (RAG) has shown promise in enhancing recommendation systems by incorporating external context into large language model prompts. However, existing RAG-based approaches often rely on static retrieval heuristics and fail to capture nuanced user preferences in dynamic recommendation scenarios. In this work, we introduce ARAG, an Agentic Retrieval-Augmented Generation framework for Personalized Recommendation, which integrates a multi-agent collaboration mechanism into the RAG pipeline. To better understand the long-term and session behavior of the user, ARAG leverages four specialized LLM-based agents: a User Understanding Agent that summarizes user preferences from long-term and session contexts, a Natural Language Inference (NLI) Agent that evaluates semantic alignment between candidate items retrieved by RAG and inferred intent, a context summary agent that summarizes the findings of NLI agent, and an Item Ranker Agent that generates a ranked list of recommendations based on contextual fit. We evaluate ARAG accross three datasets. Experimental results demonstrate that ARAG significantly outperforms standard RAG and recency-based baselines, achieving up to 42.1% improvement in NDCG@5 and 35.5% in Hit@5. We also, conduct an ablation study to analyse the effect by different components of ARAG. Our findings highlight the effectiveness of integrating agentic reasoning into retrieval-augmented recommendation and provide new directions for LLM-based personalization.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21931
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation
Maragheh, Reza Yousefi
Vadla, Pratheek
Gupta, Priyank
Zhao, Kai
Inan, Aysenur
Yao, Kehui
Xu, Jianpeng
Kanumala, Praveen
Cho, Jason
Kumar, Sushant
Information Retrieval
Artificial Intelligence
Computation and Language
Multiagent Systems
I.2.11; I.2.7; H.3.3
Retrieval-Augmented Generation (RAG) has shown promise in enhancing recommendation systems by incorporating external context into large language model prompts. However, existing RAG-based approaches often rely on static retrieval heuristics and fail to capture nuanced user preferences in dynamic recommendation scenarios. In this work, we introduce ARAG, an Agentic Retrieval-Augmented Generation framework for Personalized Recommendation, which integrates a multi-agent collaboration mechanism into the RAG pipeline. To better understand the long-term and session behavior of the user, ARAG leverages four specialized LLM-based agents: a User Understanding Agent that summarizes user preferences from long-term and session contexts, a Natural Language Inference (NLI) Agent that evaluates semantic alignment between candidate items retrieved by RAG and inferred intent, a context summary agent that summarizes the findings of NLI agent, and an Item Ranker Agent that generates a ranked list of recommendations based on contextual fit. We evaluate ARAG accross three datasets. Experimental results demonstrate that ARAG significantly outperforms standard RAG and recency-based baselines, achieving up to 42.1% improvement in NDCG@5 and 35.5% in Hit@5. We also, conduct an ablation study to analyse the effect by different components of ARAG. Our findings highlight the effectiveness of integrating agentic reasoning into retrieval-augmented recommendation and provide new directions for LLM-based personalization.
title ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation
topic Information Retrieval
Artificial Intelligence
Computation and Language
Multiagent Systems
I.2.11; I.2.7; H.3.3
url https://arxiv.org/abs/2506.21931