发表机构
Enterpret（Enterpret）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出客户上下文图方法，通过统一建模客户与业务上下文，提升客户反馈分析质量，在9,432条真实数据上以0.961分显著优于现有检索增强系统。
AI 中文摘要
组织越来越多地使用前沿语言模型来分析客户反馈，但答案质量也取决于这些反馈如何被组织起来并变得可用。我们定义了一个“客户上下文图”，作为客户和业务上下文的统一模型。类型化关系连接客户对象（反馈、对话、用户和账户）、运营对象（工单、支持代理、机会和竞争对手）以及分析或行动对象（分类概念、证据、洞察、工作项和结果）。这使得代理不仅能调查客户说了什么，还能调查为什么、谁受到影响、随后采取了什么行动、谁负责以及问题是否已解决。在本实验中，该图由公开的 Cursor 反馈填充；同一架构可以支持任何类型的反馈来源。我们在相同的 9,432 条公开 Cursor 反馈记录上，使用 30 个现实的产品、事件、比较和元数据问题，比较了 Agentic RAG、Deep Research Agent 和基于客户上下文图的代理。在没有详尽真实标签的情况下，我们使用一个比较性评分标准对响应进行联合评分，涵盖答案质量（覆盖度和组织性）、分析深度（具体性和分解度）以及证据质量（引用支持和可追溯性），该评分标准基于 30 个问题中的 28 个进行校准。我们根据声明对引用的记录进行抽样，并对三个维度进行等权加权。在此对齐的评分标准下，基于客户上下文图的代理总体得分为 0.961，而 Deep Research Agent 为 0.710，Agentic RAG 为 0.651，并且在 30 对配对问题中的 27 对上领先 Deep Research Agent（符号检验 p < 10^(-5)；在 30 对中的 26 对上严格最优）。其最大优势在于分析深度（0.967 对 0.642），这反映了更具体、分层发展的发现，并带有量化的主题和可追溯的证据。
英文摘要
Organizations increasingly use frontier language models to analyze customer feedback, but answer quality also depends on how that feedback is organized and made available. We define a \emph{customer context graph} as a unified model of customer and business context. Typed relationships connect customer objects (feedback, conversations, users, and accounts), operational objects (tickets, support agents, opportunities, and competitors), and analytical or action objects (taxonomy concepts, evidence, insights, work items, and outcomes). This lets an agent investigate not only what customers say, but why, who is affected, what action followed, who owns it, and whether it was resolved. For this experiment, the graph is populated from public Cursor feedback; the same architecture can support any type of feedback source. We compare Agentic RAG, a Deep Research Agent, and a Customer Context Graph-backed Agent on the same 9,432 public Cursor feedback records using 30 realistic product, incident, comparison, and metadata questions. Without exhaustive ground truth, we jointly score responses on answer quality (coverage and organization), analytical depth (specificity and decomposition), and evidence quality (citation support and traceability), using a comparative rubric calibrated on 28 of the 30 questions. We sample cited records against their claims and weight the three dimensions equally. Under this aligned rubric, the Customer Context Graph-backed Agent scores 0.961 overall, versus 0.710 for the Deep Research Agent and 0.651 for Agentic RAG, and leads the Deep Research Agent on 27 of 30 paired questions (sign-test p < 10^(-5); strictly best on 26 of 30). Its largest advantage is analytical depth (0.967 versus 0.642), reflecting more specific, hierarchically developed findings with quantified themes and traceable evidence...
