Image de couverture de livre

ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Bufang, Xu, Lilin, Zeng, Liekang, Guo, Yunqi, Jiang, Siyang, Lu, Wenrui, Liu, Kaiwei, Li, Yixuan, Jiang, Xiaofan, Xing, Guoliang, Yan, Zhenyu
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Computation and Language Human-Computer Interaction
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions
par: Yang, Bufang, et autres
Publié: (2025)

An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior Understanding
par: Jiang, Siyang, et autres
Publié: (2025)

Pro$^2$Assist: Continuous Step-Aware Proactive Assistance with Multimodal Egocentric Perception for Long-Horizon Procedural Tasks
par: Xu, Lilin, et autres
Publié: (2026)

SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams
par: Yang, Bufang, et autres
Publié: (2026)

PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devices
par: Liu, Kaiwei, et autres
Publié: (2025)

SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactions
par: Yang, Bufang, et autres
Publié: (2024)

DrHouse: An LLM-empowered Diagnostic Reasoning System through Harnessing Outcomes from Sensor Data and Expert Knowledge
par: Yang, Bufang, et autres
Publié: (2024)

Synera: Synergistic LLM Serving across Device and Cloud at Scale
par: Wang, Genglin, et autres
Publié: (2025)

ProAgent: Building Proactive Cooperative Agents with Large Language Models
par: Zhang, Ceyao, et autres
Publié: (2023)

A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
par: Jiang, Siyang, et autres
Publié: (2025)

Visualizing the Invisible: A Generative AR System for Intuitive Multi-Modal Sensor Data Presentation
par: Guo, Yunqi, et autres
Publié: (2024)

EgoLog: Ego-Centric Fine-Grained Daily Log with Ubiquitous Wearables
par: He, Lixing, et autres
Publié: (2025)

VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments
par: Yang, Bufang, et autres
Publié: (2024)

ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data
par: Tang, Yuanbo, et autres
Publié: (2026)

Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices
par: Ye, Shengyuan, et autres
Publié: (2024)

Exploring the Capabilities of LLMs for IMU-based Fine-grained Human Activity Understanding
par: Xu, Lilin, et autres
Publié: (2025)

ProAct: A Dual-System Framework for Proactive Embodied Social Agents
par: Zhang, Zeyi, et autres
Publié: (2026)

AgentFold: Long-Horizon Web Agents with Proactive Context Management
par: Ye, Rui, et autres
Publié: (2025)

Social Catalysts, Not Moral Agents: The Illusion of Alignment in LLM Societies
par: Hu, Yueqing, et autres
Publié: (2026)

From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench
par: Xu, Ke, et autres
Publié: (2026)

Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agents
par: Tao, Dehao, et autres
Publié: (2026)

Unified Context Evolution for LLM Agents
par: Zhu, Zixuan, et autres
Publié: (2026)

ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent
par: Zhao, Yuheng, et autres
Publié: (2025)

Training Proactive and Personalized LLM Agents
par: Sun, Weiwei, et autres
Publié: (2025)

SecAgent: Efficient Mobile GUI Agent with Semantic Context
par: Xie, Yiping, et autres
Publié: (2026)

FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents
par: Jia, Haoxuan, et autres
Publié: (2026)

TDBench: A Benchmark for Top-Down Image Understanding with Reliability Analysis of Vision-Language Models
par: Hou, Kaiyuan, et autres
Publié: (2025)

AutoContext: Instance-Level Context Learning for LLM Agents
par: Cai, Kuntai, et autres
Publié: (2025)

Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
par: Yang, Chengyuan, et autres
Publié: (2026)

ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
par: Liu, Tianjian, et autres
Publié: (2025)

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
par: Lu, Yaxi, et autres
Publié: (2024)

Auditing Agent Harness Safety
par: Liu, Chengzhi, et autres
Publié: (2026)

Push-1 is PSPACE-complete, and the automated verification of motion planning gadgets
par: DeStefano, Zachary, et autres
Publié: (2025)

SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking
par: Zhu, Xiangyang, et autres
Publié: (2025)

AgentCTG: Harnessing Multi-Agent Collaboration for Fine-Grained Precise Control in Text Generation
par: Zhou, Xinxu, et autres
Publié: (2025)

Lancelot: Towards Efficient and Privacy-Preserving Byzantine-Robust Federated Learning within Fully Homomorphic Encryption
par: Jiang, Siyang, et autres
Publié: (2024)

Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?
par: Liu, Xiaoze, et autres
Publié: (2026)

Morae: Proactively Pausing UI Agents for User Choices
par: Peng, Yi-Hao, et autres
Publié: (2025)

Towards Human-centered Proactive Conversational Agents
par: Deng, Yang, et autres
Publié: (2024)

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
par: Jiang, Pengcheng, et autres
Publié: (2026)