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

arXiv: https://arxiv.org/abs/2603.16207 · HTML: https://mlsanity.com/paper/2603.16207/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 11 of 11)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners](https://mlsanity.com/paper/2307.01928/) (2023)
- [Intention Analysis Makes LLMs A Good Jailbreak Defender](https://mlsanity.com/paper/2401.06561/) (2024)
- [IoT-LLM: a framework for enhancing Large Language Model reasoning from real-world sensor data](https://mlsanity.com/paper/2410.02429/) (2024)
- [HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices](https://mlsanity.com/paper/2505.19628/) (2025)
- [IoT-LM: Large Multisensory Language Models for the Internet of Things](https://mlsanity.com/paper/2407.09801/) (2024)
- ["Get ready for a party": Exploring smarter smart spaces with help from large language models](https://mlsanity.com/paper/2303.14143/) (2023)
- [AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment](https://mlsanity.com/paper/2506.04089/) (2025)
- [ChatIoT: Large Language Model-based Security Assistant for Internet of Things with Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.09896/) (2025)
- [Integrating Disambiguation and User Preferences into Large Language Models for Robot Motion Planning](https://mlsanity.com/paper/2404.14547/) (2024)

## Built on by (most cited first, 1 of 1)

- [Auto-Policy, not Auto-Skill: Compiled Agent Skills for the Physical World](https://mlsanity.com/paper/2608.25091/) (2026)

## Abstract (arXiv)

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.