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 [2, 52]. The prevailing approach [17, 31, 34, 36] 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 [5, 57, 61], present in behavioral patterns, absent from any retrieval index. For complex agentic tasks it 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 human attention, the digitally observable interaction signatures of each worker, encoding not just what they did but the sequence in which they did it, along with 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 qualitatively distinct 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. On a sales lead identification task, 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 human attention is its most reliable ground truth.

翻译：在企业运营中，AI智能体任务所需的上下文分散在记录系统、静态信息存储库和通信渠道中。所存储的是系统状态，即实际发生工作的有损表示[2, 52]。当前主流方法[17, 31, 34, 36]通过将请求内容与存储内容进行匹配来实现检索；对于窄范围请求，该方法效果良好。但合成质量取决于了解需要呈现什么以及如何解读它：这些是每个组织、团队和个体特有的知识[5, 57, 61]，存在于行为模式中，却不在任何检索索引里。对于复杂的智能体任务，该方法失效：真实线索率低，虚假线索率高，且模型缺乏改进机制。我们提出X-SYNTH——一个基于人类注意力的企业上下文合成框架，它利用每个工作者可数字观察的交互特征，不仅编码其行为结果，还编码行为顺序及隐含奖励信号。无需外部标注即可区分产生正向结果的行为轨迹与未产生正向结果的行为轨迹。X-SYNTH将每个个体的行为基线建模为数字孪生特征（DTS），并针对每个个体和每次查询，从七种性质不同的注意力过滤器中选择：比例型、逆比例型、差异型、循环型、比较型、顺序型和集合型，以识别具有因果相关性的活动特征。通过四阶段流水线，基于行为模式而非查询嵌入来生成排序上下文。在销售线索识别任务中，未辅助的前沿模型实现了9.5%的真实线索率（TLR）和90.5%的虚假线索率（FLR）。经X-SYNTH增强后，TLR提升至61.9%（提升6.5倍），而FLR降至18.8%。企业上下文合成并非检索问题，而是相关性问题，而人类注意力是其最可靠的真相来源。