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.
@article{arxiv.2604.08000,
title = {PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory},
author = {Zhifei Xie and Zongzheng Hu and Fangda Ye and Xin Zhang and Haobo Chai and Zihang Liu and Pengcheng Wu and Guibin Zhang and Yue Liao and Xiaobin Hu and Deheng Ye and Chunyan Miao and Shuicheng Yan},
journal= {arXiv preprint arXiv:2604.08000},
year = {2026}
}