ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems
By: Bufang Yang , Lilin Xu , Liekang Zeng and more
Potential Business Impact:
Helps smart glasses help you before you ask.
Large Language Model (LLM) agents are emerging to transform daily life. However, existing LLM agents primarily follow a reactive paradigm, relying on explicit user instructions to initiate services, which increases both physical and cognitive workload. In this paper, we propose ProAgent, the first end-to-end proactive agent system that harnesses massive sensory contexts and LLM reasoning to deliver proactive assistance. ProAgent first employs a proactive-oriented context extraction approach with on-demand tiered perception to continuously sense the environment and derive hierarchical contexts that incorporate both sensory and persona cues. ProAgent then adopts a context-aware proactive reasoner to map these contexts to user needs and tool calls, providing proactive assistance. We implement ProAgent on Augmented Reality (AR) glasses with an edge server and extensively evaluate it on a real-world testbed, a public dataset, and through a user study. Results show that ProAgent achieves up to 33.4% higher proactive prediction accuracy, 16.8% higher tool-calling F1 score, and notable improvements in user satisfaction over state-of-the-art baselines, marking a significant step toward proactive assistants. A video demonstration of ProAgent is available at https://youtu.be/pRXZuzvrcVs.
Similar Papers
AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistance
Artificial Intelligence
Helps computers find information before you ask.
Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
Artificial Intelligence
Helps computers solve problems before you ask.
AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistance
Artificial Intelligence
Helps computers find information before you ask.