Proactivity is a core expectation for AGI. Prior work remains largely confined to laboratory settings, leaving a clear gap in real-world proactive agent: depth, complexity, ambiguity, precision and real-time constraints. We study this setting, where useful intervention requires inferring latent needs from ongoing context and grounding actions in evolving user memory under latency and long-horizon constraints. We first propose DD-MM-PAS (Demand Detection, Memory Modeling, Proactive Agent System) as a general paradigm for streaming proactive AI agent. We instantiate this paradigm in Pask, with streaming IntentFlow model for DD, a hybrid memory (workspace, user, global) for long-term MM, PAS infra framework and introduce how these components form a closed loop. We also introduce LatentNeeds-Bench, a real-world benchmark built from user-consented data and refined through thousands of rounds of human editing. Experiments show that IntentFlow matches leading Gemini3-Flash models under latency constraints, while identifying deeper user intent.

翻译：主动性是通用人工智能（AGI）的核心期望。先前的研究大多局限于实验环境，在真实世界主动智能体所需的深度、复杂程度、模糊性、精确度以及实时约束方面存在明显差距。我们对此类场景展开研究，其中有效的干预需要从持续上下文中推断潜在需求，并在延迟和长期约束条件下，基于不断演化的用户记忆来实施行动。我们首先提出DD-MM-PAS（需求检测、记忆建模、主动智能体系统）作为流式主动人工智能智能体的一般范式。我们在Pask中实例化该范式，包括用于需求检测的流式IntentFlow模型、用于长期记忆建模的混合记忆结构（工作区记忆、用户记忆、全局记忆）、PAS基础设施框架，并介绍这些组件如何形成闭环。我们还提出了LatentNeeds-Bench，这是一个基于用户同意数据构建、并通过数千轮人工编辑精炼的真实世界基准测试。实验表明，IntentFlow在延迟约束下性能与领先的Gemini3-Flash模型相当，同时能识别更深层次的用户意图。