With the rapid development of Large Language Models (LLMs), LLM-based agents have been widely adopted in various fields, becoming essential for autonomous decision-making and interactive tasks. However, current work typically relies on prompt design or fine-tuning strategies applied to vanilla LLMs, which often leads to limited effectiveness or suboptimal performance in complex agent-related environments. Although LLM optimization techniques can improve model performance across many general tasks, they lack specialized optimization towards critical agent functionalities such as long-term planning, dynamic environmental interaction, and complex decision-making. Although numerous recent studies have explored various strategies to optimize LLM-based agents for complex agent tasks, a systematic review summarizing and comparing these methods from a holistic perspective is still lacking. In this survey, we provide a comprehensive review of LLM-based agent optimization approaches, categorizing them into parameter-driven and parameter-free methods. We first focus on parameter-driven optimization, covering fine-tuning-based optimization, reinforcement learning-based optimization, and hybrid strategies, analyzing key aspects such as trajectory data construction, fine-tuning techniques, reward function design, and optimization algorithms. Additionally, we briefly discuss parameter-free strategies that optimize agent behavior through prompt engineering and external knowledge retrieval. Finally, we summarize the datasets and benchmarks used for evaluation and tuning, review key applications of LLM-based agents, and discuss major challenges and promising future directions. Our repository for related references is available at https://github.com/YoungDubbyDu/LLM-Agent-Optimization.

翻译：随着大型语言模型（LLM）的快速发展，基于LLM的智能体已在多个领域得到广泛应用，成为自主决策与交互任务的关键技术。然而，当前研究通常依赖于对基础LLM进行提示设计或微调策略，这在复杂的智能体相关环境中往往效果有限或表现欠佳。尽管LLM优化技术能够提升模型在众多通用任务上的性能，但其缺乏针对智能体关键功能（如长期规划、动态环境交互和复杂决策）的专门优化。尽管近期已有大量研究探索了多种优化基于LLM的智能体以应对复杂任务的方法，但仍缺乏从整体视角系统梳理与比较这些策略的综述性研究。本文全面回顾了基于LLM的智能体优化方法，将其归纳为参数驱动与无参数两类。我们首先聚焦于参数驱动优化，涵盖基于微调的优化、基于强化学习的优化以及混合策略，并深入分析了轨迹数据构建、微调技术、奖励函数设计和优化算法等关键环节。此外，本文简要讨论了通过提示工程和外部知识检索实现智能体行为优化的无参数策略。最后，我们总结了用于评估与调优的数据集和基准测试，回顾了基于LLM的智能体的主要应用场景，并探讨了当前面临的核心挑战与未来潜在研究方向。相关参考文献库已发布于 https://github.com/YoungDubbyDu/LLM-Agent-Optimization。