PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory

arXiv:2604.08000v1 Announce Type: cross Abstract: 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.

Related

• HyperMem: Hypergraph Memory for Long-Term Conversations
• TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
• Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
• Prompt reinforcing for long-term planning of large language models
• Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces

Source: arXiv cs.CL | 2026-04-10