arXiv 2603.162072026-03-17cs.AI

主动拒绝与 grounded 执行：一种双阶段意图分析范式用于安全高效的 AIoT 智能家居

Proactive Rejection and Grounded Execution: A Dual-Stage Intent Analysis Paradigm for Safe and Efficient AIoT Smart Homes

School of Information and Electronic Engineering (Sussex Artificial Intelligence Institute), Zhejiang Gongshang University（信息与电子工程学院（Sussex人工智能研究院），浙江工商大学）；Sussex Artificial Intelligent Institute, Zhejiang Gongshang University（Sussex人工智能研究院，浙江工商大学）；Department of Engineering and Design, University of Sussex（工程与设计系， Sussex大学）；Artificial Intelligence Research Institute, Shenzhen MSU-BIT University（人工智能研究院，深圳MSU-BIT大学）；College of Computer Science and Software Engineering, Shenzhen University（计算机科学与软件工程学院，深圳大学）；Department of Electrical and Computer Engineering, The University of British Columbia（电气与计算机工程系，不列颠哥伦比亚大学）

Xinxin Jin, Zhengwei Ni, Zhengguo Sheng, Victor C. M. Leung

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出双阶段意图感知框架，通过语义防火墙和确定性验证器，解决LLM在IoT中的可靠性与交互效率问题，提升家居任务执行精度与用户干扰最小化。

摘要：

随着大型语言模型（LLMs）从信息提供者转变为物联网中的具身代理，它们面临可靠性与交互效率的显著挑战。直接执行LLM生成的指令往往导致实体幻觉（例如尝试控制不存在的设备）。同时，现有迭代框架（如SAGE）面临交互频率困境，来回摇摆于鲁莽执行与过度用户提问之间。为了解决这些问题，我们提出双阶段意图感知（DS-IA）框架。该框架将高层用户意图理解与低层物理执行分离。具体而言，第一阶段充当语义防火墙，通过检查当前家居状态来过滤无效指令并解决模糊命令。第二阶段则采用确定性级联验证器——一个严格、逐步的规则检查器，按顺序验证房间、设备和能力，以确保动作在物理上可能之前执行。在HomeBench和SAGE基准上的广泛实验表明，DS-IA实现了精确匹配（EM）率为58.56%（比基线高出超过28%），并将无效指令的拒绝率提高到87.04%。对SAGE基准的评估进一步表明，DS-IA通过平衡主动查询与基于状态的推理解决了交互频率困境。具体而言，它将自主成功率（无需不必要的用户干预解决任务）从42.86%提升到71.43%，同时在识别真正需要人类澄清的不可约模糊性方面保持高精度。这些结果凸显了该框架通过准确的环境接地来最小化用户干扰的能力。

英文摘要：

As Large Language Models (LLMs) transition from information providers to embodied agents in the Internet of Things (IoT), they face significant challenges regarding reliability and interaction efficiency. Direct execution of LLM-generated commands often leads to entity hallucinations (e.g., trying to control non-existent devices). Meanwhile, existing iterative frameworks (e.g., SAGE) suffer from the Interaction Frequency Dilemma, oscillating between reckless execution and excessive user questioning. To address these issues, we propose a Dual-Stage Intent-Aware (DS-IA) Framework. This framework separates high-level user intent understanding from low-level physical execution. Specifically, Stage 1 serves as a semantic firewall to filter out invalid instructions and resolve vague commands by checking the current state of the home. Stage 2 then employs a deterministic cascade verifier-a strict, step-by-step rule checker that verifies the room, device, and capability in sequence-to ensure the action is actually physically possible before execution. Extensive experiments on the HomeBench and SAGE benchmarks demonstrate that DS-IA achieves an Exact Match (EM) rate of 58.56% (outperforming baselines by over 28%) and improves the rejection rate of invalid instructions to 87.04%. Evaluations on the SAGE benchmark further reveal that DS-IA resolves the Interaction Frequency Dilemma by balancing proactive querying with state-based inference. Specifically, it boosts the Autonomous Success Rate (resolving tasks without unnecessary user intervention) from 42.86% to 71.43%, while maintaining high precision in identifying irreducible ambiguities that truly necessitate human clarification. These results underscore the framework's ability to minimize user disturbance through accurate environmental grounding.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。