Distributed Artificial Intelligence-Generated Content (AIGC) has attracted increasing attention. However, it faces two significant challenges: how to maximize the subjective Quality of Experience (QoE) and how to enhance the energy efficiency, which are particularly pronounced in widely adopted Generative Diffusion Model (GDM)-based AIGC services for image generation. In this paper, we propose a novel user-centric Interactive AI (IAI) approach for service management, with a distributed GDM-based AIGC framework, prioritizing efficient and collaborative GDM deployment. Specifically, we restructure the GDM's inference process, i.e., the denoising chain, to enable users' semantically similar prompts to share a portion of diffusion steps. Furthermore, to maximize the users' subjective QoE, we propose an IAI approach, i.e., Reinforcement Learning With Large Language Models Interaction (RLLI), which utilizes Large Language Model (LLM)-empowered generative agents to replicate users interaction, providing real-time and subjective QoE feedback that reflects a spectrum of user personalities. Lastly, we present the GDM-based Deep Deterministic Policy Gradient (G-DDPG) algorithm, adapted to the proposed RLLI framework, for effective communication and computing resource allocation while considering user subjective personalities and dynamic wireless environments in decision-making. Simulation results show that G-DDPG can increase the sum QoE by 15%, compared with the conventional DDPG algorithm.

翻译：分布式人工智能生成内容（AIGC）近年来备受关注，然而其面临两大关键挑战：如何最大化用户主观体验质量（QoE）以及如何提升能源效率。这些问题在基于生成扩散模型（GDM）的图像生成AIGC服务中尤为突出。本文面向分布式GDM驱动的AIGC框架，提出一种以用户为中心的新型交互式人工智能（IAI）服务管理方法，重点实现高效协同的GDM部署。具体而言，我们重构了GDM的推理过程（即去噪链），使得用户语义相似的提示词能够共享部分扩散步骤。为最大化用户主观QoE，我们提出一种IAI方法——基于大语言模型交互的强化学习（RLLI），该方法利用大语言模型（LLM）赋能的生成式智能体模拟用户交互，提供反映多种用户个性的实时主观QoE反馈。最后，我们提出适应RLLI框架的基于GDM的深度确定性策略梯度（G-DDPG）算法，在决策中兼顾用户主观个性与动态无线环境，实现高效的通信与计算资源分配。仿真结果表明，与传统DDPG算法相比，G-DDPG可将总QoE提升15%。