LinkedIn的智能客服系统能自动进化，无需重训练模型即可持续提升服务质量。
Self-evolving Agentic Customer Support System at LinkedIn
- 通过闭环自进化机制动态优化提示词与检索策略
- 上线测试中问答自解决率提升9.0%，取消请求自处理提升4.8%
- 适合追求长期稳定运行的大型企业级AI客服部署
企业客服环境瞬息万变，政策、产品功能和知识库持续更新，传统静态助手易失效且维护成本高。我们提出LinkedIn的自进化智能代理支持系统，将检索增强生成与进化式自动提示结合，并构建模块化生产对齐评估框架，实现无需重训练基础模型的安全持续优化。系统将提示词、检索与评估构成闭环版本化工作流，设有运营防护机制。离线仿真与消融实验表明，相比原始RAG和基线代理，该系统显著降低幻觉并提升回答完整性。在生产环境为期两周的用户随机A/B测试中，集成自进化流程使问答自解决率提升9.0个百分点，取消请求自处理率提升4.8个百分点，路由准确率提升30.6个百分点。结果验证了真实企业场景下可扩展的自进化AI代理的可行性。
原文摘要 · Abstract (English)
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.
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。