用数字注意力建模工作行为，提升企业线索推荐准确率。
X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Digital Human Attention
- 基于数字人类注意力构建个体行为基线，识别关键工作模式。
- 线索推荐真阳性率从9.5%提升至61.9%，假阳性率降至18.8%。
- 适合需要高精度决策支持的企业级AI应用开发者。
在企业运营中，完成AI代理任务所需上下文分散于各类系统、静态信息库和沟通渠道中。现有存储内容仅为系统状态，是实际工作过程的失真表示。当前检索方法依赖请求内容与存储信息匹配，对窄范围任务有效，但合成质量受限于对‘该展示什么’和‘如何解读’的认知——这些知识存在于组织、团队及个人的行为模式中，却未被索引记录。以向销售人员推荐企业价值线索为例，现有方法表现不佳：真线索率低、假线索率高，且模型无改进机制。本文提出X-SYNTH框架，基于可数字化观察的人类注意力（即每位员工的操作痕迹），捕捉其行动内容、顺序及隐式反馈信号。成功结果前的行为轨迹可被区分，无需外部标注。每个个体建立数字孪生签名（DTS），并根据个体与查询动态选择七种注意力滤波器（比例、逆比例、差分、递归、对比、序列、集体）。四阶段流程整合基于行为模式的排序上下文。未经增强的前沿模型真线索率仅9.5%，假线索率达90.5%；引入X-SYNTH后，真线索率升至61.9%（提升6.5倍），假线索率降至18.8%。企业上下文合成本质是相关性问题，而数字人类注意力是最可靠的真相基础。
原文摘要 · Abstract (English)
In enterprise operations, the context required for an AI agent task is scattered across systems of record, static information stores, and communication channels. What is stored is system state, a lossy representation of the work that actually happened. The prevailing approach retrieves by matching request content to what is stored; for narrow requests this works well. But synthesis quality depends on knowing what to surface and how to interpret it: knowledge specific to each organization, team, and individual, present in behavioral patterns, absent from any retrieval index. For the agentic task of proposing enterprise-valuable leads to sellers, this approach breaks down: True Lead Rate is low, False Lead Rate is high, and the model has no mechanism to improve. We present X-SYNTH, a framework for enterprise context synthesis grounded in digital human attention, the digitally observable interaction signatures of each worker, encoding what they did, the sequence in which they did it, and implicit reward signals. Behavioral traces preceding positive outcomes are distinguishable from those that did not, without external labeling. X-SYNTH models each individual's behavioral baseline as a Digital Twin Signature (DTS) and selects among seven attention filters, Proportional, Inverse, Differential, Recurrent, Comparative, Sequential, and Collective, per individual and per query, to identify causally relevant activity signatures. A four-stage pipeline assembles ranked context grounded in behavioral patterns rather than query embeddings. A frontier model unaided achieves 9.5% True Lead Rate (TLR) with 90.5% False Lead Rate (FLR). Augmented with X-SYNTH, TLR rises to 61.9% (6.5x) while FLR falls to 18.8%. Enterprise context synthesis is not a retrieval problem. It is a relevance problem, and digital human attention is its most reliable ground truth.
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。