With the prosperity of e-commerce and web applications, Recommender Systems (RecSys) have become an indispensable and important component, providing personalized suggestions that cater to user preferences. While Deep Neural Networks (DNNs) have achieved significant advancements in enhancing recommender systems, these DNN-based methods still exhibit some limitations, such as inferior capabilities to effectively capture textual side information about users and items, difficulties in generalization to various recommendation scenarios, and reasoning on their predictions, etc. Meanwhile, the development of Large Language Models (LLMs), such as ChatGPT and GPT-4, has revolutionized the fields of Natural Language Processing (NLP) and Artificial Intelligence (AI), due to their remarkable abilities in fundamental responsibilities of language understanding and generation, as well as impressive generalization capabilities and reasoning skills. As a result, recent studies have actively attempted to harness the power of LLMs to enhance recommender systems. Given the rapid evolution of this research direction in recommender systems, there is a pressing need for a systematic overview that summarizes existing LLM-empowered recommender systems. Therefore, in this survey, we comprehensively review LLM-empowered recommender systems from various perspectives including pre-training, fine-tuning, and prompting paradigms. More specifically, we first introduce the representative methods to learn user and item representations, leveraging LLMs as feature encoders. Then, we systematically review the emerging advanced techniques of LLMs for enhancing recommender systems from three paradigms, namely pre-training, fine-tuning, and prompting. Finally, we comprehensively discuss the promising future directions in this emerging field.

Wireless-networked control system (WNCS) connecting sensors, controllers, and actuators via wireless communications is a key enabling technology for highly scalable and low-cost deployment of control systems in the Industry 4.0 era. Despite the tight interaction of control and communications in WNCSs, most existing works adopt separate design approaches. This is mainly because the co-design of control-communication policies requires large and hybrid state and action spaces, making the optimal problem mathematically intractable and difficult to be solved effectively by classic algorithms. In this article, we systematically investigate deep-learning (DL)-based estimator-control-scheduler co-design for a model-unknown nonlinear WNCS over wireless fading channels. In particular, we propose a co-design framework with the awareness of the sensor’s Age-of-Information (AoI) states and dynamic channel states. We propose a novel deep reinforcement learning (DRL)-based algorithm for controller and scheduler optimization utilizing both model-free and model-based data. An AoI-based importance sampling algorithm that takes into account the data accuracy is proposed for enhancing learning efficiency. We also develop novel schemes for enhancing the stability of joint training. Extensive experiments demonstrate that the proposed joint training algorithm can effectively solve the estimation–control–scheduling co-design problem in various scenarios and provide significant performance gain compared to separate designs and some benchmark policies.

The rapid development of Artificial Intelligence (AI), and especially Agentic AI, is reshaping how work is organized at both the individual and organizational levels. An emerging organizational form—the One-Person Agentic Company (OPAC)—allows a solo or a few founders to orchestrate specialized agent swarms to manage complex business functions through real-time analysis and adaptive coordination. Unlike the traditional one-person company, which offers strong individual control but limited scalability, OPAC extends one-person productivity by combining human leadership with a multi-agent workforce powered by large language models and multimodal models. Despite growing interest, OPAC has emerged as an important research direction, yet the field remains in its early stages. Existing research is fragmented across AI foundation, multi-agent systems, human–computer interaction, and management. This survey provides the first systematic review of research relevant to OPACs. We define OPAC through four organizational characteristics from both technical and management perspectives. We further compare OPACs with traditional companies in terms of organizational composition, cost structure, efficiency, development logic, authority, and risk. We then organize the literature into four thematic areas critical to the technical and managerial design of OPAC. Specifically, we review how OPACs are structured and operate, how agent-related resources are allocated and governed, how such organizations develop through agent and workflow updates, and how reliability, accountability, and human control can be maintained amid increasing agentic delegation. By connecting advances in LLM-based agents and multi-agent systems with management research on organizational design, resource allocation, adaptation, and governance, this survey clarifies the current research landscape of OPACs, highlights critical open challenges, and outlines future directions for scalable and trustworthy human-led agentic enterprises.

Recommender systems play a vital role in alleviating information overload and enriching users' online experience. In the era of large language models (LLMs), LLM-based recommender systems have emerged as a prevalent paradigm for advancing personalized recommendations. Recently, retrieval-augmented generation (RAG) has drawn growing interest to facilitate the recommendation capability of LLMs, incorporating useful information retrieved from external knowledge bases. However, as a rich source of up-to-date information, the web remains under-explored by existing RAG-based recommendations. In particular, unique challenges are posed from two perspectives: one is to generate effective queries for web retrieval, considering the inherent knowledge gap between web search and recommendations; another challenge lies in harnessing online websites that contain substantial noisy content. To tackle these limitations, we propose WebRec, a novel web-based RAG framework, which takes advantage of the reasoning capability of LLMs to interpret recommendation tasks into queries of user preferences that cater to web retrieval. Moreover, given noisy web-retrieved information, where relevant pieces of evidence are scattered far apart, an insightful MP-Head is designed to enhance LLM attentions between distant tokens of relevant information via message passing. Extensive experiments have been conducted to demonstrate the effectiveness of our proposed web-based RAG methods in recommendation scenarios.