Proactive agents read user activity as text and call an LLM on every event to decide whether to act. But user activity is not natively text: it is a structured event stream of (actor, verb, object, timestamp) tuples that the operating system already maintains in graph form. Rendering the structure as text and asking an LLM to recover it is a round-trip the system never had to take. We treat the always-on signal as graph updates rather than text and use a small temporal-graph-learning (TGL) model as the encoder: one forward pass yields a per-event trigger probability and a per-entity routing score, and only the downstream agent (turning a small structured handoff into a fluent user-facing sentence) is an LLM call, invoked only when the trigger fires. TGL improves F1 on each of 14 backbones (mean +16.7, up to +46.0); in trigger-architecture comparisons, one TGL checkpoint gives the strongest trigger AUCs and the most stable deployed threshold. It runs at 11.13 ms per event on a GPU server and 13.99 ms on a consumer laptop, approximately 4--7x and 12--83x faster than every single-forward LLM-as-trigger configuration tested in each regime, with an approximately 220 MiB BF16 resident footprint deployable on-device alongside the privacy-sensitive activity stream it consumes.

翻译：主动型代理将用户活动读取为文本，并在每个事件上调用大语言模型以决定是否采取行动。但用户活动本质上并非文本：它是一个结构化的（参与者、动作、对象、时间戳）元组事件流，操作系统已以图形式维护这些数据。将结构渲染为文本并让大语言模型恢复其结构，是系统本无需进行的往返过程。我们将常开信号视为图更新而非文本，并使用小型时态图学习模型作为编码器：一次前向传播生成每个事件的触发概率和每个实体的路由分数，仅当下游代理（将小型结构化交接转换为面向用户的流畅语句）需要调用大语言模型时，才在触发信号激活时执行调用。时态图学习模型在14个骨干网络上的F1指标均有提升（平均提升16.7，最高达46.0）；在触发架构对比中，单一时态图学习检查点实现了最强的触发AUC和最稳定的部署阈值。该模型在GPU服务器上以每个事件11.13毫秒运行，在消费级笔记本上为13.99毫秒，分别比两种运行环境下所有单次前向传播的大语言模型触发配置快约4-7倍和12-83倍，其BF16驻留内存占用约220 MiB，可与所消费的隐私敏感活动流一同部署在端侧设备上。