首次系统分析智能体记忆机制，揭示不同设计对性能与成本的影响。
Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
- 构建四维分类体系，梳理记忆系统的架构差异。
- 实测十种系统，发现写入与读取路径成本分布受设计影响显著。
- 提出10条优化建议，适用于大规模部署的智能体系统。
大语言模型智能体在长期任务中需持续维护交互历史记忆，实现规模化部署依赖于跨会话持久存储、检索与更新能力。当前涌现多种记忆系统，涵盖扁平检索、基于LLM的提取、事实库整合及代理控制流等。然而其系统级行为尚未被充分刻画。本文首次开展智能体记忆系统的系统性表征：首先提出面向系统的四轴分类法；其次构建阶段感知的性能剖析工具，量化构建、检索与生成各环节开销；接着在两个基准套件上评估十种代表性系统，揭示设计选择如何影响写入与读取路径的成本分布；最后提出十条系统设计建议，涵盖构造调度、能力下限、查询量分摊、新鲜度-延迟权衡及集群管理等关键问题。
原文摘要 · Abstract (English)
LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale requires agents to persistently store, retrieve, and update their own memory across sessions. A rich ecosystem of agent memory systems has emerged spanning flat retrieval, LLM-mediated extraction, consolidating fact stores, and agentic control flows. Yet, their system-level behavior remains uncharacterized. We present the first systems characterization of agent memory. First, we introduce a system-oriented taxonomy classifying agent memory systems along four axes. Second, we build a phase-aware profiling harness attributing cost to construction, retrieval, and generation. Third, we characterize ten representative systems across two benchmark suites, uncovering how design choices shift cost across the write and read paths. Finally, we derive 10 system recommendations covering construction scheduling, capability floors, amortization via query volume, freshness-latency tradeoffs, and fleet-scale management.
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。