Scholarlink

<p>In this study, we introduce MO-MAB-KG, an adaptive Multi-objective multi-armed bandit framework designed to enhance retrieval strategies in Knowledge Graph-augmented, Retrieval-Augmented Generation (KG-RAG) systems operating under non-stationary conditions. The proposed framework addresses two key challenges in real-world deployment: (1) adapting to dynamic environments driven by shifting query distributions and continual updates to knowledge graphs, and (2) simultaneously optimizing multiple, often conflicting objectives such as accuracy, retrieval recall, and latency. MO-MAB-KG offers three principal innovations: (i) a contextual bandit model that dynamically selects among dense, sparse, knowledge graph-based, and hybrid retrieval strategies based on query-specific features; (ii) a reward function grounded in the Generalized Gini Index to support principled multi-objective optimization; and (iii) an online learning mechanism that incrementally updates retrieval strategies based on implicit user feedback. Experiments on real-world QA datasets from a Nexacro-based GenAI chatbot assistant service demonstrate that MO-MAB-KG improves the hit rate by 12.7% and reduces response latency by a factor of up to 3.2 compared to state-of-the-art baselines, while maintaining robustness under distributional shifts. These results underscore the practical effectiveness of MO-MAB-KG for intelligent and adaptive retrieval in continuously evolving industrial environments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

MO-MAB-KG: a multi-objective bandit framework for adaptive and robust knowledge graph-augmented retrieval in dynamic environments

  • 期刊论文

  • 发表日期：

    2026年7月2日

查看全文
  • Yong-Jae Lee

摘要

In this study, we introduce MO-MAB-KG, an adaptive Multi-objective multi-armed bandit framework designed to enhance retrieval strategies in Knowledge Graph-augmented, Retrieval-Augmented Generation (KG-RAG) systems operating under non-stationary conditions. The proposed framework addresses two key challenges in real-world deployment: (1) adapting to dynamic environments driven by shifting query distributions and continual updates to knowledge graphs, and (2) simultaneously optimizing multiple, often conflicting objectives such as accuracy, retrieval recall, and latency. MO-MAB-KG offers three principal innovations: (i) a contextual bandit model that dynamically selects among dense, sparse, knowledge graph-based, and hybrid retrieval strategies based on query-specific features; (ii) a reward function grounded in the Generalized Gini Index to support principled multi-objective optimization; and (iii) an online learning mechanism that incrementally updates retrieval strategies based on implicit user feedback. Experiments on real-world QA datasets from a Nexacro-based GenAI chatbot assistant service demonstrate that MO-MAB-KG improves the hit rate by 12.7% and reduces response latency by a factor of up to 3.2 compared to state-of-the-art baselines, while maintaining robustness under distributional shifts. These results underscore the practical effectiveness of MO-MAB-KG for intelligent and adaptive retrieval in continuously evolving industrial environments.