让AI自动优化事实修正条目，提高知识库检索准确率。
Iterate Until Retrieved: Factual Nugget Optimization for Discoverable Continual Corrections in Agentic RAG
- 用真实反馈生成小而准的事实修正条目
- 通过迭代测试优化条目，直到能被正确检索到
- 适合需要持续更新专业知识的B2B客服系统
在复杂的B2B场景中，智能检索增强生成（Agentic RAG）系统常收到自由形式的反馈。本文聚焦可操作的事实修正，将其转化为紧凑的知识条目（称为事实片段）。提出迭代片段优化（INO）方法，在索引阶段利用生产环境的RAG系统作为测试框架：生成初始片段，用触发查询及其改写句进行探测，分析失败的检索与回答轨迹，不断修正片段直至可被发现。在两家公司生产的两个B2B知识辅助系统上评估，包括产品支持代理和工单处理代理，INO在自动化与人工评估中均显著提升事实修正的可发现性与使用率，优于基线方法。
原文摘要 · Abstract (English)
Agentic retrieval-augmented generation (RAG) systems in complex B2B (business-to-business) settings may often receive free-form response feedback. Rather than generic feedback signals such as style, preference, or overall response quality, we focus on actionable factual corrections. We identify these instances and convert them into compact knowledge-base entries, which we call factual nuggets. We introduce Iterative Nugget Optimization (INO), an index-time optimization method that uses the production agentic RAG as a test harness: it creates an initial nugget, probes it with the triggering query and paraphrases, reflects over failed retrieval and answer traces, and revises the nugget until it is discoverable. We evaluate INO with two production B2B knowledge-assistance agents across multiple companies that use our system: a product support agent that answers questions over company-specific knowledge bases, and a support ticket agent that assists support engineers. INO consistently improves results over baselines in terms of discoverability and usage of factual corrections, in automated and human evaluations.
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。