发表机构
Microsoft（微软公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对职场智能体，提出构建多分辨率人类行为轨迹解读框架，在生产力套件数据上验证其结构稳定性与预测有效性，表明需按问题需求选择时间粒度解读轨迹。
AI 中文摘要
运行时轨迹正成为理解智能体系统的核心载体，但现有解读大多聚焦于智能体的行为。职场智能体面临的互补问题是：解读围绕它们的人类活动。数小时的低层级事件承载着关于用户状态的丰富证据，但粒度过细难以直接推理；将其展平为单一序列或压缩为单个嵌入，都把“总结用户行为”视为只有一个正确答案。我们则认为，行为解读依赖于分辨率：同一轨迹应能在不同时间分辨率下提供多个可被处理的解读。我们构建了一个多分辨率词汇表，包含语义归一化算子、重复 motif、连贯片段和日级节奏，每类都保留了自身时间尺度下的显著结构。将其应用于来自某大型商业生产力套件的6.67亿条人类归因事件（涉及5万名用户、100个组织），共得到120种算子类型、数千个motif、25种片段类型和5种日节奏原型。我们通过真实遥测数据验证：在2000名用户的不相交样本上重新运行整个流程，能恢复相同的分类体系（结构稳定性）；在留存用户上，完整表示预测用户下一个片段的准确性优于单一算子基线，相对宏F1提升17%（预测有效性），说明这些抽象不仅能描述，还保留了与未来相关的信息。控制分辨率的消融实验显示，没有单一分辨率能适配所有问题：同一轨迹的不同智能体相关问题，在不同分辨率下能得到最佳解答。因此，面向智能体的行为轨迹解读应采用多分辨率且查询条件化的方式：智能体应能访问问题所需的时间粒度，而非采用单一通用总结。
英文摘要
Runtime traces are becoming a central substrate for understanding agentic systems, yet interpretation has focused largely on what the agent did. Workplace agents face the complementary problem: interpreting the human activity that surrounds them. Hours of low-level events carry rich evidence about a user's state but are too granular to reason over directly, and flattening them into one stream or compressing them into a single embedding both treat "summarize the user's behavior" as if it had one correct answer. We argue instead that behavioral interpretation is resolution-dependent: the same trace should admit multiple addressable interpretations at different temporal resolutions. We construct a multi-resolution vocabulary of semantically normalized operators, recurring motifs, coherent episodes, and day-level rhythms, each preserving the structure salient at its own horizon. Applied to 667 million human-attributed events from a large commercial productivity suite (50,000 users, 100 organizations), it yields 120 operator types, thousands of motifs, 25 episode types, and five day-rhythm archetypes. We validate it on real telemetry: re-running the entire pipeline on a disjoint 2,000-user sample recovers the same taxonomy (structural stability), and on held-out users the full representation forecasts a user's next episode more accurately than a flat-operator baseline, a 17% relative macro-F1 gain (predictive validity), so the abstractions preserve future-relevant information rather than merely describe it. A controlled resolution ablation then shows that no single level is optimal across questions: different agent-facing questions about the same trace are best answered at different resolutions. Behavioral trace interpretation for agents should therefore be multi-resolution and query-conditioned: an agent should access the temporal grain a question needs, not one universal summary.
