PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
This addresses the gap in real-world proactive agents for users needing intelligent assistance in complex, ambiguous environments, representing a novel method for a known bottleneck.
The paper tackles the problem of building proactive AI agents for real-world settings by proposing a general paradigm and system (PASK) that infers latent user needs and grounds actions in long-term memory under latency constraints, achieving performance matching leading models while identifying deeper intent.
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.