Since the advent of personal computing devices, intelligent personal assistants (IPAs) have been one of the key technologies that researchers and engineers have focused on, aiming to help users efficiently obtain information and execute tasks, and provide users with more intelligent, convenient, and rich interaction experiences. With the development of smartphones and IoT, computing and sensing devices have become ubiquitous, greatly expanding the boundaries of IPAs. However, due to the lack of capabilities such as user intent understanding, task planning, tool using, and personal data management etc., existing IPAs still have limited practicality and scalability. Recently, the emergence of foundation models, represented by large language models (LLMs), brings new opportunities for the development of IPAs. With the powerful semantic understanding and reasoning capabilities, LLM can enable intelligent agents to solve complex problems autonomously. In this paper, we focus on Personal LLM Agents, which are LLM-based agents that are deeply integrated with personal data and personal devices and used for personal assistance. We envision that Personal LLM Agents will become a major software paradigm for end-users in the upcoming era. To realize this vision, we take the first step to discuss several important questions about Personal LLM Agents, including their architecture, capability, efficiency and security. We start by summarizing the key components and design choices in the architecture of Personal LLM Agents, followed by an in-depth analysis of the opinions collected from domain experts. Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.
The Internet of Things (IoT) is continuously growing to connect billions of smart devices anywhere and anytime in an Internet-like structure, which enables a variety of applications, services and interactions between human and objects. In the future, the smart devices are supposed to be able to autonomously discover a target device with desired features and generate a set of entirely new services and applications that are not supervised or even imagined by human beings. The pervasiveness of smart devices, as well as the heterogeneity of their design and functionalities, raise a major concern: How can a smart device efficiently discover a desired target device? In this paper, we propose a Social-Aware and Distributed (SAND) scheme that achieves a fast, scalable and efficient device discovery in the IoT. The proposed SAND scheme adopts a novel device ranking criteria that measures the device's degree, social relationship diversity, clustering coefficient and betweenness. Based on the device ranking criteria, the discovery request can be guided to travel through critical devices that stand at the major intersections of the network, and thus quickly reach the desired target device by contacting only a limited number of intermediate devices. With the help of such an intelligent device discovery as SAND, the IoT devices, as well as other computing facilities, software and data on the Internet, can autonomously establish new social connections with each other as human being do. They can formulate self-organized computing groups to perform required computing tasks, facilitate a fusion of a variety of computing service, network service and data to generate novel applications and services, evolve from the individual aritificial intelligence to the collaborative intelligence, and eventually enable the birth of a robot society.