paper-with-me

홈 › Papers

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

2026-04-09 · Zhifei Xie, Zongzheng Hu, Fangda Ye, Xin Zhang, Haobo Chai, Zihang Liu, Pengcheng Wu, Guibin Zhang, Yue Liao, Xiaobin Hu, Deheng Ye, Chunyan Miao, Shuicheng Yan arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.08000

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents

2026-03-09 · Yuxiang Chai, Shunye Tang, Han Xiao, Rui Liu 외 arxiv

Current Graphical User Interface (GUI) agents operate primarily under a reactive paradigm: a user must provide an explicit instruction for the agent to execute a task. However, an intelligent AI assistant should be proac…

ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions

2025-05-20 · Bufang Yang, Lilin Xu, Liekang Zeng, Kaiwei Liu 외

Recent advances in Large Language Models (LLMs) have propelled intelligent agents from reactive responses to proactive support. While promising, existing proactive agents either rely exclusively on observations from encl…

Parser States Already Know: Structure-Conditioned KV Persistence for Structured Generation

2026-08-28 · Linze Wu, Xinrui Chen arxiv

Structured generation underpins large language model (LLM) agents that produce JSON, SQL, and function calls, where a single wrong field can cause the downstream action to fail. Constrained decoding already tracks parser…

IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning

2026-02-03 · Haohao Luo, Zexi Li, Yuexiang Xie, Wenhao Zhang 외 arxiv

Deep Research (DR) agents extend Large Language Models (LLMs) beyond parametric knowledge by autonomously retrieving and synthesizing evidence from large web corpora into long-form reports, enabling a long-horizon agenti…

Reinforcement Learning

PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records

2026-01-14 · Yibo Lyu, Gongwei Chen, Rui Shao, Weili Guan 외 arxiv

While GUI agents have shown strong performance under explicit and completion instructions, real-world deployment requires aligning with users' more complex implicit intents. In this work, we highlight Hierarchical Implic…