In the last few years, the bottleneck of bandwidth in Internet of Thing (IoT) has driven expectations to figure out new ways to preprocess the information needed to be transmitted. The ways which were used before are not smart enough and they cannot align to the users’ need. Large language model (LLM)-based intelligent agent is a very hot concept in AI community, which aims to save various problems via adapting LLM to different industries. In this article, we present a collective intelligent agent system for the IoT (CASIT) that is a pioneering LLM-agent-based IoT system. We put forward a IoT framework that can be used to lots of scenarios. CASIT refers to a system based on multiple intelligent LLM agents, which realizes complex tasks through cooperation and makes full use of collective intelligence. In order to solve the problems, we designed the Memory Mechanism and Summary Mechanism that enable LLMs to efficiently process the data by comparing historical data with Local Knowledge and Chat History in the prompt. After experimental verification, we have found that our framework could accurately conclude the abnormal information, and it outperforms the single LLM system when we input 200 sets of temperature and humidity data from five different places. The system provides a new solution and method for information processing in all IoT systems. Our framework may also provide refreshing ideas for edge computing and semantic communication.

Human–Object Interaction (HOI) detection seeks to identify the relationships between humans and objects in images that play a pivotal role in high-level vision tasks and biomimetic systems, such as biomimetic robotics, intelligent prosthetics, and embodied AI for intent understanding. However, existing approaches that rely solely on visual appearance features are susceptible to background interference, which adversely affects detection accuracy. Inspired by the biomimetic dual-stream mechanism of biological visual perception, we propose a Transformer-based HOI detection model with a dual-branch parallel fusion architecture, incorporating a skeleton topology branch alongside the standard image branch. The skeleton branch leverages a Graph Convolutional Network (GCN) to explicitly model spatial–kinematic relationships between human keypoints and objects, providing fine-grained topological priors to complement visual appearance features before joint decoding. Our approach achieves 51.6% Mean Average Precision (mAP) on the Verbs in Common Objects in Context (V-COCO) dataset, outperforming the Transformer-based HOI baseline by 2.7 mAP points, highlighting its effectiveness in enhancing perceptual robustness for biomimetic interactive applications.