# Reinforcement Learning With LLMs Interaction For Distributed Diffusion Model Services

arXiv: https://arxiv.org/abs/2311.11094 · HTML: https://mlsanity.com/paper/2311.11094/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2023.

## Built on by (most cited first, 7 of 7)

- [Generative AI Agents with Large Language Model for Satellite Networks via a Mixture of Experts Transmission](https://mlsanity.com/paper/2404.09134/) (2024)
- [Generative AI-Driven Human Digital Twin in IoT-Healthcare: A Comprehensive Survey](https://mlsanity.com/paper/2401.13699/) (2024)
- [Vision Language Model-Empowered Contract Theory for AIGC Task Allocation in Teleoperation](https://mlsanity.com/paper/2407.17428/) (2024)
- [Generative Diffusion-based Contract Design for Efficient AI Twins Migration in Vehicular Embodied AI Networks](https://mlsanity.com/paper/2410.01176/) (2024)
- [SAGE: Semantic-Aware Shared Sampling for Efficient Diffusion](https://mlsanity.com/paper/2509.15865/) (2025)
- [LMM-Incentive: Large Multimodal Model-based Incentive Design for User-Generated Content in Web 3.0](https://mlsanity.com/paper/2510.04765/) (2025)
- [Joint Energy Management and Coordinated AIGC Workload Scheduling for Distributed Data Centers: A Diffusion-Aided Reward Shaping Approach](https://mlsanity.com/paper/2605.02965/) (2026)

## Abstract (arXiv)

Distributed Artificial Intelligence-Generated Content (AIGC) has attracted significant attention, but two key challenges remain: maximizing subjective Quality of Experience (QoE) and improving energy efficiency, which are particularly pronounced in widely adopted Generative Diffusion Model (GDM)-based image generation services. In this paper, we propose a novel user-centric Interactive AI (IAI) approach for service management, with a distributed GDM-based AIGC framework that emphasizes efficient and cooperative deployment. The proposed method restructures the GDM inference process by allowing users with semantically similar prompts to share parts of the denoising chain. 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 user interaction, providing real-time and subjective QoE feedback aligned with diverse user personalities. Lastly, we present the GDM-based Deep Deterministic Policy Gradient (GDDPG) algorithm, adapted to the proposed RLLI framework, to allocate communication and computing resources effectively while accounting for subjective user traits and dynamic wireless conditions. Simulation results demonstrate that G-DDPG improves total QoE by 15% compared with the standard DDPG algorithm.