运营和维护(O&M)大型在线引擎系统(eg,搜索,推荐和广告)需要大量人力来发布监控,警报响应,和根本原因分析。尽管基于 LLM 的代理对于此类操作场景, 具有固有的适用性，但阻碍其实际部署的关键瓶颈不在于推理,，而在于编排能力 - 特别是, 相关数据的精确选择(，包括指标, 日志, 和更改事件) 以及适用的知识(，包括手册定义的规则和根据经验得出的从业者经验)，针对每个单独的操作事件量身定制。不加区别地提供所有信号会导致稀释和幻觉,，而手动策划事件到(数据,知识)的映射在数十个每日发布中是棘手的。在这里，我们向扁鹊,提出了一个具有三个贡献的代理操作框架: (i) 统一操作范式,，将日常O&M操作抽象为三个规范模式:释放拦截,主动检查,和警报根本原因分析; (ii) 灵活的技能安排, 每个预定义的技能都明确定义了每个特定上下文所需的数据和操作知识。此类技能可以由 LLM 代理, 自动生成和更新，也可以由待命工程师通过自然语言指令进行迭代优化。 (iii) 统一的自我进化机制,，其中每个校正信号启用两条并行的进化路径:，将事件记忆提炼成知识, 并有针对性地改进技能。部署在快手电商搜索引擎上,扁鹊减少报警量75%,，根源分析准确率达到80%,，平均解决时间缩短50%,以上，线下评估通过率达到99.0%。代码位于此 https URL。
Operating and maintaining (O&M) large-scale online engine systems (eg, search, recommendation and advertising) demands substantial human effort for release monitoring, alert response, and root cause analysis. Despite the inherent suitability of LLM-based agents for such operational scenarios, the critical bottleneck impeding their practical deployment lies not in reasoning, but in orchestration capability - specifically, the precise selection of relevant data (encompassing metrics, logs, and change events) and applicable knowledge (including handbook-defined rules and empirically derived practitioner experience) tailored to each individual operational event. Feeding all signals indiscriminately causes dilution and hallucination, while manually curating the event-to-(data, knowledge) mapping is intractable under dozens of daily releases. Here we present Bian Que, an agentic operating framework with three contributions: (i) The unified operational paradigm, which abstracts routine daily O&M actions into three canonical patterns: release interception, proactive inspection, and alert root cause analysis; (ii) The flexible Skill Arrangement, each predefined Skill explicitly defines the requisite data and operational knowledge for each specific context. Such Skills can be automatically generated and updated by LLM agents, and can also be iteratively optimized by on-call engineers via natural language instructions. (iii) The unified self-evolving mechanism, where each correction signal enables two parallel evolutionary pathways: distilling event memory into knowledge, and targeted refinement of Skills. Deployed on the e-commerce search engine of KuaiShou, Bian Que reduces alert volume by 75%, achieves 80% root-cause analysis accuracy, cuts mean time to resolution by over 50%, and attains a 99.0% pass rate on offline evaluations. Codes are at this https URL.
科目: 人工智能 (cs.AI); 多代理系统 (cs.MA)
Subjects: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)