面向LinkedIn招聘代理的分层长期语义记忆
Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent
AI总结:
提出分层长期语义记忆(HLTM)框架,通过构建模式对齐的记忆树,实现可扩展的语义知识摄入、隐私感知存储、低延迟检索和透明溯源,在LinkedIn招聘助手应用中使答案正确率提升超5%、检索F1提升超10%。
摘要:
大型语言模型(LLM)代理越来越多地应用于实际产品中,其中个性化和上下文感知的用户交互至关重要。实现此类能力的核心是代理的长期语义记忆系统,该系统从嘈杂的纵向行为数据中提取隐式和显式信号,以结构化形式存储,并支持低延迟检索。构建工业级LLM代理长期记忆面临五大挑战:可扩展性、低延迟检索、隐私约束、适应性和可观测性。我们提出了分层长期语义记忆(HLTM)框架,该框架将文本数据组织成模式对齐的记忆树,在多个粒度级别捕获语义知识,从而实现可扩展的摄入、隐私感知存储、低延迟检索和透明溯源;HLTM还进一步融入了适应机制以泛化到不同用例。在LinkedIn招聘助手上的广泛评估表明,HLTM使答案正确率提升超过5%,检索F1提升超过10%,同时显著推进了查询与索引延迟之间的帕累托前沿。HLTM已全面部署在LinkedIn招聘助手中,用于支持生产招聘工作流中的核心个性化功能。
英文摘要:
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.
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。