做智能体系统架构的团队终于有了第一份记忆系统性能基准——10 条设计建议直接指导工程决策，建议做 Agent 框架或记忆中间件的开发者点开细读。
该论文首次对 LLM 智能体的记忆系统进行系统性表征，提出了面向系统的四轴分类法，并构建了阶段感知的性能分析工具。研究覆盖了 10 个代表性记忆系统在两个基准套件上的行为，揭示了设计选择如何影响写入和读取路径的代价。最终给出了 10 条系统设计建议，涵盖构建调度、能力下限、查询量摊销、新鲜度-延迟权衡及集群管理。这项工作为构建高效、可扩展的长期记忆智能体提供了关键指导。
Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
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.