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

• URL: http://arxiv.org/abs/2605.28175v2
• Date: Fri, 29 May 2026 13:34:06 GMT
• Title: Mixture-of-Experts Knowledge Graph Retrieval-Augmented Generation for Multi-Agent LLM-based Recommendation
• Abstract summary: We propose a cooperative multi-agent framework for knowledge graph retrieval-augmented generation (KG-RAG) recommendations.<n>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.
• Score: 56.36851606088493
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 However, LLM-based recommender systems often rely on parametric knowledge and suffer from outdated knowledge, motivating knowledge graph retrieval-augmented generation (KG-RAG) to ground recommendations on structured, up-to-date KGs.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.

Related papers

• Multi-hop Reasoning via Early Knowledge Alignment [68.28168992785896]
  Early Knowledge Alignment (EKA) aims to align Large Language Models with contextually relevant retrieved knowledge.<n>EKA significantly improves retrieval precision, reduces cascading errors, and enhances both performance and efficiency.<n>EKA proves effective as a versatile, training-free inference strategy that scales seamlessly to large models.
  arXiv  Detail & Related papers  (2025-12-23T08:14:44Z)
• Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? [57.28763506780752]
  GraphFlow is a framework that efficiently retrieves accurate and diverse knowledge required for real-world queries from text-rich KGs.<n>It outperforms strong KG-RAG baselines, including GPT-4o, by 10% on average in hit rate and recall.<n>It also shows strong generalization to unseen KGs, demonstrating its effectiveness and robustness.
  arXiv  Detail & Related papers  (2025-10-18T17:06:49Z)
• Towards Open-World Retrieval-Augmented Generation on Knowledge Graph: A Multi-Agent Collaboration Framework [21.896955284099334]
  Large Language Models (LLMs) have demonstrated strong capabilities in language understanding and reasoning.<n>Retrieval-Augmented Generation (RAG) addresses this limitation by incorporating external knowledge sources.<n>We propose AnchorRAG, a novel multi-agent collaboration framework for open-world RAG without the predefined anchor entities.
  arXiv  Detail & Related papers  (2025-09-01T08:26:12Z)
• Enhancing Large Language Models (LLMs) for Telecommunications using Knowledge Graphs and Retrieval-Augmented Generation [52.8352968531863]
  Large language models (LLMs) have made significant progress in general-purpose natural language processing tasks.<n>This paper presents a novel framework that combines knowledge graph (KG) and retrieval-augmented generation (RAG) techniques to enhance LLM performance in the telecom domain.
  arXiv  Detail & Related papers  (2025-03-31T15:58:08Z)
• Graph Retrieval-Augmented LLM for Conversational Recommendation Systems [52.35491420330534]
  G-CRS (Graph Retrieval-Augmented Large Language Model for Conversational Recommender Systems) is a training-free framework that combines graph retrieval-augmented generation and in-context learning.<n>G-CRS achieves superior recommendation performance compared to existing methods without requiring task-specific training.
  arXiv  Detail & Related papers  (2025-03-09T03:56:22Z)
• Boosting Knowledge Graph-based Recommendations through Confidence-Aware Augmentation with Large Language Models [19.28217321004791]
  Large Language Models (LLMs) offer a promising way to improve the quality and relevance of Knowledge Graphs for recommendation tasks.<n>We propose the Confidence-aware KG-based Recommendation Framework with LLM Augmentation (CKG-LLMA), a novel framework that combines KGs and LLMs for recommendation task.<n>The framework includes: (1) an LLM-based subgraph augmenter for enriching KGs with high-quality information, (2) a confidence-aware message propagation mechanism to filter noisy triplets, and (3) a dual-view contrastive learning method to integrate user-item interactions and KG data.
  arXiv  Detail & Related papers  (2025-02-06T02:06:48Z)
• FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs [17.477161619378332]
  We propose a novel flexible modular KG-RAG framework, termed FRAG, which synergizes the advantages of both approaches.<n>By using the query text instead of the Knowledge Graph, FRAG improves retrieval quality while maintaining flexibility.
  arXiv  Detail & Related papers  (2025-01-17T05:19:14Z)
• LLM is Knowledge Graph Reasoner: LLM's Intuition-aware Knowledge Graph Reasoning for Cold-start Sequential Recommendation [47.34949656215159]
  Large Language Models (LLMs) can be considered databases with a wealth of knowledge learned from the web data.<n>We propose a LLM's Intuition-aware Knowledge graph Reasoning model (LIKR)<n>Our model outperforms state-of-the-art recommendation methods in cold-start sequential recommendation scenarios.
  arXiv  Detail & Related papers  (2024-12-17T01:52:15Z)
• Reasoning over User Preferences: Knowledge Graph-Augmented LLMs for Explainable Conversational Recommendations [58.61021630938566]
  Conversational Recommender Systems (CRSs) aim to provide personalized recommendations by capturing user preferences through interactive dialogues.<n>Current CRSs often leverage knowledge graphs (KGs) or language models to extract and represent user preferences as latent vectors, which limits their explainability.<n>We propose a plug-and-play framework that synergizes LLMs and KGs to reason over user preferences, enhancing the performance and explainability of existing CRSs.
  arXiv  Detail & Related papers  (2024-11-16T11:47:21Z)
• Comprehending Knowledge Graphs with Large Language Models for Recommender Systems [13.270018897057293]
  We propose a novel method called CoLaKG to improve knowledge graphs.<n>By employing the item-centered subgraph extraction and prompt engineering, it can accurately understand the local information.<n>In addition, through the semantic-based retrieval module, each item is enriched by related items from the entire knowledge graph.
  arXiv  Detail & Related papers  (2024-10-16T04:44:34Z)
• KG-RAG: Bridging the Gap Between Knowledge and Creativity [0.0]
  Large Language Model Agents (LMAs) face issues such as information hallucinations, catastrophic forgetting, and limitations in processing long contexts. This paper introduces a KG-RAG (Knowledge Graph-Retrieval Augmented Generation) pipeline to enhance the knowledge capabilities of LMAs. Preliminary experiments on the ComplexWebQuestions dataset demonstrate notable improvements in the reduction of hallucinated content.
  arXiv  Detail & Related papers  (2024-05-20T14:03:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.