arXiv cs.MA· Pradipta Ghosh, Gaurav Mitra, Shripad Nadgowda, Akshil Shah, Junyu Liu, Canturk Isci, Syamla Bandla, Xinyao Hu, Onkar Deshpande, Anik Dasgupta·· 2 天前AI 评分32
Diviner：面向大规模基础设施、由人类治理自适应调整的智能体根因分析系统
Diviner: Agentic RCA with Human-Governed Adaptation for Large-Scale Infrastructure
AI 导读
Meta 提出智能体根因分析系统 Diviner，围绕 Encode、Execute、Evaluate、Adapt 四阶段可靠性生命周期运行，用经过审核的事件语料和服务负责人经验构建带版本范围的技能、工作流、类型化工具与事件知识图谱。
正文 · 原文
Abstract:Root-cause analysis (RCA) in large-scale distributed systems is challenging because a single symptom can cross service, data, configuration, compute, and organizational boundaries. Responders must assemble incomplete evidence and coordinate experts who hold different parts of the causal path. Generic language-model agents do not solve this problem through tool access alone: they can use stale or mistimed context, interpret failed queries as absent symptoms, report unsupported system state, and overload observability services designed for human-paced use.
We present Diviner (Domain-Informed Verifiable Incident Navigation through Evidence and Review), an agentic RCA system operating at Meta and organized around a four-stage reliability lifecycle. Encode combines a large corpus of reviewed incidents with service-owner expertise to produce scoped, versioned skills, workflows, typed tools, and an incident knowledge graph. Execute uses an adaptive Lead and context-isolated workers to apply relevant knowledge to point-in-time evidence and maintain evidence-linked hypotheses. Evaluate compares saved investigation trajectories with responder-reviewed outcomes to measure exact cause, useful direction, and Groundedness. Adapt uses recurring gaps and on-call feedback to derive focused operational- knowledge updates, admitting them only after replay, quality checks, and owner approval.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.21281 [cs.AI] |
| (or arXiv:2610.21281v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21281 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Pradipta Ghosh [view email]
[v1]
Thu, 15 Oct 2026 05:20:23 UTC (4,985 KB)
来源：arXiv cs.MA · arxiv.org