# Mixture-of-Experts Knowledge Graph Retrieval-Augmented Generation for Multi-Agent LLM-based Recommendation

arXiv: https://arxiv.org/abs/2605.28175 · HTML: https://mlsanity.com/paper/2605.28175/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RAG for recommendation, one of 15 directions in Retrieval-augmented generation.
- Builds on 33 of its 54 references that are in the map.
- First posted on arXiv 27 May 2026.

## Placed in

- Retrieval-augmented generation / [RAG for recommendation](https://mlsanity.com/rag/rag-for-recommendation/)
- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)
- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 30 of 33)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation](https://mlsanity.com/paper/2305.00447/) (2023)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering](https://mlsanity.com/paper/2402.07630/) (2024)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [Let Your Graph Do the Talking: Encoding Structured Data for LLMs](https://mlsanity.com/paper/2402.05862/) (2024)
- [AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems](https://mlsanity.com/paper/2310.09233/) (2023)
- [CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation](https://mlsanity.com/paper/2310.19488/) (2023)
- [ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation](https://mlsanity.com/paper/2308.11131/) (2023)
- [Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering](https://mlsanity.com/paper/2309.11206/) (2023)
- [Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation](https://mlsanity.com/paper/2501.02226/) (2025)
- [LLaRA: Large Language-Recommendation Assistant](https://mlsanity.com/paper/2312.02445/) (2023)
- [NoteLLM: A Retrievable Large Language Model for Note Recommendation](https://mlsanity.com/paper/2403.01744/) (2024)
- [Graph Machine Learning in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2404.14928/) (2024)
- [Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation](https://mlsanity.com/paper/2310.06491/) (2023)
- [G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation](https://mlsanity.com/paper/2502.12586/) (2025)
- [Towards Next-Generation Recommender Systems: A Benchmark for Personalized Recommendation Assistant with LLMs](https://mlsanity.com/paper/2503.09382/) (2025)
- [Collaborative Retrieval for Large Language Model-based Conversational Recommender Systems](https://mlsanity.com/paper/2502.14137/) (2025)
- [Graph Retrieval-Augmented LLM for Conversational Recommendation Systems](https://mlsanity.com/paper/2503.06430/) (2025)
- [Multi-agent Attacks for Black-box Social Recommendations](https://mlsanity.com/paper/2311.07127/) (2023)
- [STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning](https://mlsanity.com/paper/2601.03248/) (2026)

## Built on by (most cited first, 2 of 2)

- [Diffusion Language Model for Recommendation](https://mlsanity.com/paper/2607.21519/) (2026)
- [AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalization](https://mlsanity.com/paper/2609.19793/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have recently been adopted for recommendations due to their ability to understand user intent and item semantics. However, LLM-based recommender systems often rely on parametric knowledge and suffer from outdated knowledge, motivating knowledge graph retrieval-augmented generation (KG-RAG) to ground recommendations on structured, up-to-date KGs. Despite this promise, effective KG-RAG in recommendations faces great challenges. First, users' queries vary in complexity and require KG knowledge at different granularities, whereas existing methods adopt a one-size-fits-all retrieval strategy, leading to over-retrieval for simple queries and under-retrieval for complex ones. In addition, augmenting LLMs with KG knowledge requires translating graph-structured data into linear text, which may introduce noise and cause structural information loss. Moreover, the selection of retrieval granularity lacks direct supervision and must be inferred from the final recommendation after alignment and downstream utilization, making query-aware retrieval hard to learn end-to-end. To address these issues, we propose MixRAGRec, a cooperative multi-agent framework for KG-RAG recommendations. MixRAGRec integrates a Mixture-of-Experts Retrieval Agent that routes each query to a KG retrieval expert with different granularities, a Knowledge Preference Alignment Agent that converts structured knowledge into LLM-friendly natural language, and a Contrastive Learning-reinforced Recommendation Agent trained with contrastive preference feedback. Notably, we introduce Mixture-of-Experts Multi-Agent Policy Optimization (MMAPO) to train three agents under a unified objective. Extensive experiments on real-world datasets demonstrate the effectiveness of our framework.