发表机构
LinkedIn（领英公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
领英提出一种集成检索增强生成、进化自动提示与模块化评估框架的自进化智能体客户支持系统，经测试可显著提升多项支持任务指标，为企业级自进化 AI 智能体提供可行方案。
AI 中文摘要
企业支持代理在快速变化的环境中工作，政策、产品功能和知识库不断演变，使得静态助手脆弱且维护成本高昂。我们提出了领英的自进化智能体支持系统，该系统将检索增强生成（RAG）与进化自动提示以及模块化、与生产对齐的评估框架相结合，无需重新训练基础模型即可实现安全的持续改进。该系统将提示、检索和评估视为带有操作护栏的闭环、版本化工作流。离线模拟和 ablation 实验显示，与普通 RAG 和基线智能体相比，质量有明显提升，包括幻觉减少和响应完整性提高。在领英生产支持流量上进行的为期两周的用户随机 A/B 测试中，集成的自进化工作流使 QA 自助服务提升了 9.0 个百分点，取消自助服务提升了 4.8 个百分点，路由准确率提升了 30.6 个百分点。这些结果证明了在现实企业环境中构建可扩展、自进化 AI 智能体的可行路径。
英文摘要
Enterprise support agents operate in rapidly changing environments where policies, product capabilities, and knowledge bases evolve continuously, making static assistants brittle and costly to maintain. We present LinkedIn's self-evolving agentic support system, which integrates retrieval-augmented generation with evolutionary auto-prompting and a modular, production-aligned evaluation framework to enable safe, continuous improvement without retraining foundation models. The system treats prompts, retrieval, and evaluation as a closed-loop, versioned workflow with operational guardrails. Offline simulations and ablations show clear quality gains over vanilla RAG and baseline agents, including reduced hallucinations and improved response completeness. In a two-week user-randomized A/B test on LinkedIn's production support traffic, the integrated self-evolved workflow increased QA self-serve by 9.0 percentage points, cancellation self-serve by 4.8 points, and routing accuracy by 30.6 points. These results demonstrate a practical path to scalable, self-evolving AI agents in real-world enterprise settings.
