The paper "LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs" introduces a novel approach that leverages large language models (LLMs) to construct personalized reasoning graphs for recommendation systems. These graphs link a user's profile and behavioral sequences through causal and logical inferences, providing an interpretable representation of the user's interests. The approach, called LLMRG, consists of four components: chained graph reasoning, divergent extension, self-verification, and knowledge base self-improvement. The resulting reasoning graph is encoded using graph neural networks, which serve as additional input to conventional recommender systems. The paper demonstrates the effectiveness of LLMRG on benchmarks and real-world scenarios, showing that it can enhance recommendation performance without requiring extra user or item data. The authors also conduct ablation studies to validate the effectiveness of each module in the LLMRG framework, confirming the importance of the reasoning graph for accurate and explainable recommendations.The paper "LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs" introduces a novel approach that leverages large language models (LLMs) to construct personalized reasoning graphs for recommendation systems. These graphs link a user's profile and behavioral sequences through causal and logical inferences, providing an interpretable representation of the user's interests. The approach, called LLMRG, consists of four components: chained graph reasoning, divergent extension, self-verification, and knowledge base self-improvement. The resulting reasoning graph is encoded using graph neural networks, which serve as additional input to conventional recommender systems. The paper demonstrates the effectiveness of LLMRG on benchmarks and real-world scenarios, showing that it can enhance recommendation performance without requiring extra user or item data. The authors also conduct ablation studies to validate the effectiveness of each module in the LLMRG framework, confirming the importance of the reasoning graph for accurate and explainable recommendations.