An Autonomous Agent Framework for Feature-Label Extraction from Device Dialogues and Automatic Multi-Dimensional Device Hosting Planning Based on Large Language Models

2026-01-28

AI Summary

This work proposes AirAgent, a novel framework addressing the limitations of conventional home appliances in proactively sensing personalized user needs and dynamic environmental changes, particularly their lack of precise, multidimensional air management capabilities. AirAgent introduces a dual-layer memory-reasoning architecture that continuously updates user profiles through voice interaction and dynamic memory tagging. It fuses multisource contextual information via reasoning-driven planning to enable context-aware decision-making, while a semi-streaming structured output mechanism simultaneously generates interpretable reasoning chains and executable device commands. The system supports complex planning across 25 dimensions with over 20 customizable constraints, achieving a 94.9% decision accuracy in real-world scenarios and improving user satisfaction by more than 20% compared to leading commercial solutions.

Technology Category

• Multiagent Systems: Multiagent Planning
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

With the deep integration of artificial intelligence and smart home technologies, the intelligent transformation of traditional household appliances has become an inevitable trend. This paper presents AirAgent--an LLM-driven autonomous agent framework designed for home air systems. Leveraging a voice-based dialogue interface, AirAgent autonomously and personally manages indoor air quality through comprehensive perception, reasoning, and control. The framework innovatively adopts a two-layer cooperative architecture: Memory-Based Tag Extraction and Reasoning-Driven Planning. First, a dynamic memory tag extraction module continuously updates personalized user profiles. Second, a reasoning-planning model integrates real-time environmental sensor data, user states, and domain-specific prior knowledge (e.g., public health guidelines) to generate context-aware decisions. To support both interpretability and execution, we design a semi-streaming output mechanism that uses special tokens to segment the model's output stream in real time, simultaneously producing human-readable Chain-of-Thought explanations and structured, device-executable control commands. The system handles planning across 25 distinct complex dimensions while satisfying more than 20 customized constraints. As a result, AirAgent endows home air systems with proactive perception, service, and orchestration capabilities, enabling seamless, precise, and personalized air management responsive to dynamic indoor and outdoor conditions. Experimental results demonstrate up to 94.9 percent accuracy and more than 20 percent improvement in user experience metrics compared to competing commercial solutions.

Problem

• feature-label extraction
• autonomous agent
• multi-dimensional planning
• device dialogue
• personalized air management

Innovation

• Autonomous Agent
• Large Language Model
• Memory-Based Tag Extraction
• Reasoning-Driven Planning
• Semi-Streaming Output