迭代直到检索到：面向可发现持续修正的事实性片段优化在智能体RAG中的应用
Iterate Until Retrieved: Factual Nugget Optimization for Discoverable Continual Corrections in Agentic RAG
AI总结：
提出迭代片段优化（INO）方法，通过将反馈转化为事实性片段并利用生产环境智能体RAG系统迭代优化，提升事实性修正的可发现性和使用率。
摘要：
在复杂的B2B（企业对企业）环境中，智能体检索增强生成（RAG）系统经常接收自由形式的反馈。我们关注可操作的事实性修正，而非风格、偏好或整体响应质量等通用反馈信号。我们识别这些实例并将其转化为紧凑的知识库条目，称为事实性片段。我们引入迭代片段优化（INO），一种索引时优化方法，将生产环境中的智能体RAG作为测试平台：它创建初始片段，使用触发查询及其释义进行探测，反思失败的检索和回答轨迹，并修订片段直到其可被发现。我们使用两个生产B2B知识辅助代理（一个回答公司特定知识库问题的产品支持代理，以及一个协助支持工程师的支持工单代理）在多家使用我们系统的公司中评估INO。在自动化和人工评估中，INO在事实性修正的可发现性和使用率方面持续优于基线。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
