在大语言模型时代:在统一框架下的模块化架构与策略
Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
AI总结:
本文在统一框架下系统比较了多种记忆方法,设计出优于现有方法的新方法,并探讨了未来研究方向。
摘要:
记忆在基于大语言模型(LLM)的代理中成为核心模块,用于长期复杂任务(如多轮对话、游戏扮演、科学发现),其中记忆可促进知识积累、迭代推理和自我进化。文献中已提出多种记忆方法,但这些方法在相同实验设置下未被系统和全面比较。本文首先总结了一个统一框架,从高层视角整合了所有现有代理记忆方法。然后在两个知名基准上广泛比较了代表性代理记忆方法,并检验所有方法的有效性,提供详尽分析。作为实验分析的副产品,我们还通过现有方法中的模块设计出新的记忆方法,其性能优于现有最佳方法。最后,基于这些发现,我们提出了有前景的未来研究机会。我们认为,对现有方法行为的深入理解可为未来研究提供有价值的新的见解。
英文摘要:
Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative reasoning and self-evolution. A number of memory methods have been proposed in the literature. However, these methods have not been systematically and comprehensively compared under the same experimental settings. In this paper, we first summarize a unified framework that covers existing representative agent memory methods from a high-level perspective. We then extensively compare representative agent memory methods on two long-term conversational benchmarks and an agentic memory benchmark, and examine the effectiveness of representative methods, providing a thorough analysis of those methods. As a byproduct of our experimental analysis, we also design a new memory method by exploiting modules in the existing methods, which outperforms the state-of-the-art methods. Finally, based on these findings, we offer promising future research opportunities. We believe that a deeper understanding of the behavior of existing methods can provide valuable new insights for future research.
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。