发表机构
Microsoft（微软）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有RAG系统忽略故障排查案例多阶段、有状态特性的问题，提出有状态检索增强框架RAFT，在条目级检索并返回锚定轨迹，经合成与真实数据评估，显著优于基线。
AI 中文摘要
在企业客户支持中，有效的故障排查智能体依赖于从相似的历史案例中检索可操作的指导，然而现有的检索增强生成（RAG）系统将支持案例视为静态文档，忽略了其多阶段、有状态的性质。我们提出了RAFT（面向故障排查智能体的检索增强框架），一种有状态的RAG框架，它将每个已关闭的历史案例抽象为时间线条目的有向链，并在条目级别进行检索，从而呈现中间状态与当前活动案例匹配的案例，并返回以匹配状态为锚点的父案例轨迹；一个可选的案例级图通过可配置的相似性表示将案例连接起来。我们直接评估这一检索层，与评估完整智能体系统不同，这无需生产部署。由于公开的多阶段故障排查数据极为罕见，我们将基于微软学习Windows Server文档构建的合成基准与带有真实人工创建的重复标签的Apache Jira问题配对使用。RAFT在案例进展的每个阶段都优于普通RAG和GraphRAG基线，相对于最强基线具有统计显著的提升；Jira结果提供了方向性证据，表明该优势可迁移至真实案例历史。我们发布了我们的基准、实现以及Apache Jira评估集。
英文摘要
Effective troubleshooting agents in enterprise customer support depend on retrieving actionable guidance from similar historical cases, yet existing retrieval-augmented generation (RAG) systems treat support cases as static documents and overlook their multi-stage, stateful nature. We introduce RAFT (Retrieval-Augmented Framework for Troubleshooting Agents), a stateful RAG framework that abstracts each closed historical case into a directed chain of timeline entries and retrieves at the entry level, surfacing cases whose intermediate states match the active case and returning the parent-case trajectory anchored at the matched state; an optional case-level graph links cases through a configurable similarity representation. We evaluate this retrieval layer directly, which, unlike evaluating a full agent system, requires no production deployment. Because public multi-stage troubleshooting data is extremely rare, we pair a synthetic benchmark built from Microsoft Learn Windows Server documentation with real Apache Jira issues carrying human-created duplicate labels. RAFT improves Case Hit over vanilla RAG and GraphRAG baselines at every stage of case progress, with statistically significant gains over the strongest baseline; the Jira results provide directional evidence that the advantage transfers to real case histories. We release our benchmark, implementation, and the Apache Jira evaluation set.
CommentsAccepted to the EMNLP 2026 Industry Track
