用智能体框架自动匹配运维数据与知识，大幅减少告警和故障排查时间。
Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations
- 将运维操作抽象为发布拦截、主动检查、告警分析三类模式。
- 通过可自动生成更新的技能模块，精准匹配事件所需数据与经验。
- 支持工程师自然语言优化，实现持续进化，适合大规模系统运维团队。
维护大型在线系统（如搜索、推荐、广告）需要大量人力进行版本监控、告警响应和根因分析。尽管大模型智能体适合此类场景，但实际部署的关键瓶颈不在于推理能力，而在于编排能力——即针对每个运维事件精准选择相关数据（指标、日志、变更事件）和适用知识（手册规则与实践经验）。盲目输入所有信号会导致信息稀释与幻觉，而手动建立事件与数据/知识的映射在每日数十次发布下不可行。本文提出Bian Que，一个具有三项贡献的智能体运维框架：(i) 统一运维范式，将日常运维动作抽象为发布拦截、主动检查、告警根因分析三类标准模式；(ii) 灵活技能编排，每个预定义技能明确指定特定情境下的必要数据与操作知识，可由大模型自动生成并迭代优化，也可通过工程师自然语言指令持续改进；(iii) 统一自我演化机制，每次修正信号触发两条并行进化路径：将事件记忆提炼为知识，以及对技能进行针对性优化。在快手电商搜索系统上线后，告警量降低75%，根因分析准确率达80%，平均修复时间缩短超50%，离线评估通过率达99.0%。代码已开源：https://github.com/benchen4395/BianQue_Assistant。
原文摘要 · Abstract (English)
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 https://github.com/benchen4395/BianQue_Assistant.
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。