系统对比大模型代理记忆方法，发现最优组合策略。
Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
- 构建统一框架，整合主流记忆方法
- 在双对话与代理记忆基准上验证性能，新方法超越当前最优
- 适合研究大模型长期任务与记忆机制的学者
记忆成为基于大语言模型（LLM）的智能体执行长周期复杂任务（如多轮对话、游戏对战、科学发现）的核心模块，支持知识积累、迭代推理与自我演化。尽管已有多种记忆方法提出，但缺乏在相同实验设置下的系统性比较。本文首先从高层视角总结一个涵盖现有代表性代理记忆方法的统一框架；随后在两个长期对话基准和一个代理记忆基准上，对代表性方法进行广泛对比，深入分析其有效性。作为实验分析的副产物，我们通过融合现有方法中的模块设计出一种新记忆方法，性能优于当前最先进方法。最后，基于这些发现，提出未来研究的潜在方向。我们认为，对现有方法行为的深入理解将为后续研究提供宝贵洞见。
原文摘要 · Abstract (English)
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.
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。