RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents· RAFT：一种故障排除代理的状态感知检索增强框架
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
提出了一种针对故障排除代理的状态感知检索增强框架。
- 核心方法
- RAFT框架将历史案例抽象为时间线条目的有向链，以条目级别进行检索，匹配活跃案例的中间状态，并返回从匹配状态开始的父案例轨迹；可选案例级别图通过可配置的相似性表示链接案例。
- 适合谁读
- 研究者、工程师、客户服务产品设计师
- 要解决的问题
- 现有故障排除代理系统忽视了支持案例的动态多阶段特性，导致检索和生成效果不佳。
- 关键实验
- 对检索层进行了直接评估，具体实验设置和结果未提供。
- 主要贡献
- 提升了故障排除代理在企业客户服务中检索和利用历史案例的能力，更好地适应动态多阶段的故障解决过程。
- 意义与局限
- 改进了故障排除过程中的信息检索，可能显著提高客户服务效率和满意度。局限性在于模型的适用性可能受限于特定领域和数据质量。