Despite the superior performance of Large language models on many NLP tasks, they still face significant limitations in memorizing extensive world knowledge. Recent studies have demonstrated that leveraging the Retrieval-Augmented Generation (RAG) framework, combined with Knowledge Graphs that encapsulate extensive factual data in a structured format, robustly enhances the reasoning capabilities of LLMs. However, deploying such systems in real-world scenarios presents challenges: the continuous evolution of non-stationary environments may lead to performance degradation and user satisfaction requires a careful balance of performance and responsiveness. To address these challenges, we introduce a Multi-objective Multi-Armed Bandit enhanced RAG framework, supported by multiple retrieval methods with diverse capabilities under rich and evolving retrieval contexts in practice. Within this framework, each retrieval method is treated as a distinct ``arm''. The system utilizes real-time user feedback to adapt to dynamic environments, by selecting the appropriate retrieval method based on input queries and the historical multi-objective performance of each arm. Extensive experiments conducted on two benchmark KGQA datasets demonstrate that our method significantly outperforms baseline methods in non-stationary settings while achieving state-of-the-art performance in stationary environments. Code and data are available at https://github.com/FUTUREEEEEE/Dynamic-RAG.git

翻译：尽管大型语言模型在许多自然语言处理任务上表现出色，但其在记忆海量世界知识方面仍存在显著局限。近期研究表明，利用检索增强生成框架，结合以结构化形式封装大量事实数据的知识图谱，能有效增强大语言模型的推理能力。然而，在实际场景中部署此类系统面临诸多挑战：非平稳环境的持续演化可能导致性能衰退，而用户满意度要求系统在性能与响应速度之间实现精细平衡。为应对这些挑战，我们提出一种多目标多臂老虎机增强的检索增强生成框架，该框架在实践中丰富且动态演化的检索环境下，整合了多种具备不同能力的检索方法。在此框架中，每种检索方法被视为独立的"臂"。系统通过实时用户反馈适应动态环境，依据输入查询及各臂的历史多目标表现选择适宜的检索方法。在两个知识图谱问答基准数据集上的大量实验表明，我们的方法在非平稳环境下显著优于基线方法，同时在平稳环境中达到最优性能。代码与数据公开于 https://github.com/FUTUREEEEEE/Dynamic-RAG.git