探究大模型智能体记忆结构对性能的影响，发现混合记忆更抗干扰，迭代检索效果最好。
On the Structural Memory of LLM Agents
- 对比四种记忆结构与三种检索方法，系统评估其在不同任务中的表现
- 混合记忆在噪声环境下表现稳定，迭代检索普遍优于其他方法
- 研究结果可指导大模型智能体记忆系统的针对性设计
记忆在支持大语言模型（LLM）智能体进行复杂、长期交互（如问答和对话系统）中起着关键作用。尽管已提出多种记忆模块，但不同记忆结构在各类任务中的影响仍缺乏充分探索。本文研究了记忆结构与检索方法对基于LLM智能体性能的影响。具体评估了四种记忆结构：片段、知识三元组、原子事实、摘要，以及结合这些组件的混合记忆；同时比较三种常用检索方法：单步检索、重排序和迭代检索。在四个任务与六个数据集上的大量实验表明：(1) 不同记忆结构各具优势，可针对特定任务定制；(2) 混合记忆在噪声环境中表现出显著鲁棒性；(3) 迭代检索在各类场景下均优于其他方法。本研究旨在推动基于LLM智能体记忆系统的设计优化。
原文摘要 · Abstract (English)
Memory plays a pivotal role in enabling large language model~(LLM)-based agents to engage in complex and long-term interactions, such as question answering (QA) and dialogue systems. While various memory modules have been proposed for these tasks, the impact of different memory structures across tasks remains insufficiently explored. This paper investigates how memory structures and memory retrieval methods affect the performance of LLM-based agents. Specifically, we evaluate four types of memory structures, including chunks, knowledge triples, atomic facts, and summaries, along with mixed memory that combines these components. In addition, we evaluate three widely used memory retrieval methods: single-step retrieval, reranking, and iterative retrieval. Extensive experiments conducted across four tasks and six datasets yield the following key insights: (1) Different memory structures offer distinct advantages, enabling them to be tailored to specific tasks; (2) Mixed memory structures demonstrate remarkable resilience in noisy environments; (3) Iterative retrieval consistently outperforms other methods across various scenarios. Our investigation aims to inspire further research into the design of memory systems for LLM-based agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。