LinkedIn的招聘助手用分层记忆系统提升个性化推荐准确率超5%。
Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent
- 构建分层语义记忆树，按粒度组织文本数据
- 召回F1提升超10%，答案正确率提高5%以上
- 兼顾隐私、低延迟与可观察性，适合工业级应用
大型语言模型（LLM）代理在真实产品中日益普及，个性化和上下文感知的用户交互至关重要。其核心支撑是长时语义记忆系统，能从嘈杂的长期行为数据中提取显式和隐式信号，以结构化形式存储并支持低延迟检索。构建工业级长时记忆面临可扩展性、低延迟检索、隐私约束、适应性和可观测性五大挑战。本文提出分层长时语义记忆（HLTM）框架，将文本数据组织成与模式对齐的记忆树，捕捉多粒度语义知识，实现可扩展摄入、隐私友好存储、低延迟检索与透明溯源；同时引入自适应机制，增强跨场景泛化能力。在LinkedIn招聘助手上的大量评估表明，HLTM使回答正确率提升超过5%，召回F1提升超过10%，显著优化查询与索引延迟的帕累托前沿。目前，HLTM已全面部署于LinkedIn招聘助手，支撑生产环境中的核心个性化功能。
原文摘要 · Abstract (English)
Large Language Model (LLM) agents are increasingly used in real-world products, where personalized and context-aware user interactions are essential. A central enabler of such capabilities is the agent's long-term semantic memory system, which extracts implicit and explicit signals from noisy longitudinal behavioral data, stores them in a structured form, and supports low-latency retrieval. Building industrial-grade long-term memory for LLM agents raises five challenges: scalability, low-latency retrieval, privacy constraints, adaptability, and observability. We introduce the Hierarchical Long-Term Semantic Memory (HLTM) framework, which organizes textual data into a schema-aligned memory tree that captures semantic knowledge at multiple levels of granularity, enabling scalable ingestion, privacy-aware storage, low-latency retrieval, and transparent provenance; HLTM further incorporates an adaptation mechanism to generalize across diverse use cases. Extensive evaluations on LinkedIn's Hiring Assistant show that HLTM improves answer correctness by more than 5% and retrieval F1 by more than 10%, while significantly advancing the Pareto frontier between query and indexing latency. HLTM has been fully deployed in LinkedIn's Hiring Assistant to power core personalization features in production hiring workflows.
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。