综述：多臂老虎机与大语言模型的交汇
Survey: Multi-Armed Bandits Meet Large Language Models
AI总结：
本文综述多臂老虎机与大语言模型的双向融合，梳理老虎机用于优化微调、提示和响应生成，以及 LLM 增强上下文决策的方法、挑战与机遇。
摘要：
老虎机算法与大语言模型（LLM）已成为人工智能中的强大工具，各自应对决策和自然语言处理中不同但互补的挑战。本综述探讨这两个领域之间的协同潜力，重点说明老虎机算法如何提升 LLM 的性能，以及 LLM 反过来如何为改进基于老虎机的决策提供新的洞见。我们首先考察老虎机算法在优化 LLM 微调、提示工程和自适应响应生成中的作用，重点关注它们在大规模学习任务中平衡探索与利用的能力。随后，我们探讨 LLM 如何通过先进的上下文理解、动态适应以及利用自然语言推理改进策略选择，来增强老虎机算法。通过全面回顾现有研究并识别关键挑战与机遇，本综述旨在弥合老虎机算法与 LLM 之间的差距，为人工智能中的创新应用和跨学科研究铺平道路。
英文摘要：
Bandit algorithms and Large Language Models (LLMs) have emerged as powerful tools in artificial intelligence, each addressing distinct yet complementary challenges in decision-making and natural language processing. This survey explores the synergistic potential between these two fields, highlighting how bandit algorithms can enhance the performance of LLMs and how LLMs, in turn, can provide novel insights for improving bandit-based decision-making. We first examine the role of bandit algorithms in optimizing LLM fine-tuning, prompt engineering, and adaptive response generation, focusing on their ability to balance exploration and exploitation in large-scale learning tasks. Subsequently, we explore how LLMs can augment bandit algorithms through advanced contextual understanding, dynamic adaptation, and improved policy selection using natural language reasoning. By providing a comprehensive review of existing research and identifying key challenges and opportunities, this survey aims to bridge the gap between bandit algorithms and LLMs, paving the way for innovative applications and interdisciplinary research in AI.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
