To address the bottleneck of technologically advanced but cognitively limited smart buildings, this paper introduces embodied intelligence to reconstruct the intelligent paradigm of architectural space. It defines embodied intelligent space and develops a Human–Intelligence–Context framework. In this framework, space is regarded as a collaborative spatial agent with a degree of autonomy. Based on a systematic review of 293 studies published from 2017 to 2026, the paper proposes a technical adaptation loop of embodied perception, cognitive decision-making, and embodied actuation. This loop explains how space gains computability, interpretability, and actionability. The paper further develops a scenario–pathway–implementation framework from an architectural perspective. This framework clarifies how intelligent technologies can be structurally embedded into architectural systems. The findings show that embodied intelligent space supports the shift from a passive container to an autonomous spatial agent. This shift is enabled by multimodal perception, spatial large-model reasoning, and edge–cloud collaborative actuation. The study provides theoretical support and implementation pathways for sustainable and human-centered settlement environments.

With the popularity of mobile devices, a variety of motion sensors are integrated to enhance the user experience. Although existing studies demonstrated that non-acoustic motion sensors can be attacked by adversaries, they overlook the limited sampling frequencies of motion sensors (e.g., < 500 Hz) in mobile devices and are evaluated in the controlled laboratory settings. In this article, we explore a new attack model on non-acoustic motion sensors based on the off-the-shelf mobile devices. We propose a general framework named VoiceFormer to synthesize high-fidelity speeches based on the vibrations of accelerometers and gyroscopes with a low sampling frequency. Specifically, in VoiceFormer , we introduce a signal alignment approach to remove the time offsets between two nonsynchronous signals, and leverage Time Interleaved Analog-Digital-Conversion (TI-ADC) to generate a high-frequency synthetic signal (e.g., > 8 KHz) based on the vibration signals of accelerometers and gyroscopes on the same motherboard. To synthesize the high-fidelity acoustic waveforms, we propose a wavelet-based generative adversarial network to learn the spatiotemporal latent mapping between vibrations and original speech signals. Extensive experimental results demonstrate the feasibility of voice synthesis by spying the low-frequency non-acoustic motion sensors in off-the-shelf mobile devices. VoiceFormer shows impressive performance in the synthesized acoustical signals with a Mean Opinion Score of 3.38. Although there are significant differences of mobile devices in hardware settings, VoiceFormer shows robust performance in synthesizing intelligible voice signals. Our results suggest that eavesdropping an off-the-shelf mobile device remotely by fusing non-acoustic sensors is feasible.

Mobile GUI Agents powered by multimodal large language models (MLLMs) show promise in human-computer intelligence. However, current research primarily focuses on reactive task execution while lacking a comprehensive “understanding-prediction-execution” process for user intentions, which are the core requirements of active agents. In this paper, we propose the Act2Intention framework that builds an active mobile agent by integrating understanding, predicting user intentions, and executing decisions. Firstly, we constructed the Act2Intention Bench through collection and validated generation, comprising 72,511 intentions and over 700,000 actions across 52 apps, thereby establishing the first benchmark for evaluating proactive agents via continuous “intention-actions” trajectories. We further develop the Act2Intention Agent, achieving proactive services through Proactive-oriented Intention Understanding, Personalized Proactive Intention Prediction, and Experience-guided Intention Execution. Experimental results show that supervised fine-tuning on Act2Intention Bench yields absolute improvements of +32.0 Acc-S, +10.25 Acc-S, and +6.9 SSR points over non-fine-tuned counterparts under the same agent framework for intention understanding, prediction, and execution, respectively. This success underscores the necessity and value of the Act2Intention Bench, which establishes a standardized platform for developing and evaluating proactive agents and consequently paves the way for research on intention-driven human-computer interaction. To facilitate further research, we open-source our code and Act2Intention Bench at: npuNancy/Act2Intention.