Intelligent Mobile AI-Generated Content Services via Interactive Prompt Engineering and Dynamic Service Provisioning

TL;DR

This paper introduces an intelligent mobile AIGC service framework that enhances prompt quality through LLM-based engineering and IRL, and optimizes resource allocation with a diffusion-enhanced DRL algorithm, significantly improving content generation success and user experience.

Contribution

It presents a novel interactive prompt engineering method using LLMs and IRL, along with a diffusion-enhanced DRL algorithm for dynamic service provisioning in mobile AIGC environments.

Findings

Prompt engineering boosts success probability by 6.3 times.

D3PG improves user service experience by 67.8%.

Proposed methods outperform baseline approaches.

Abstract

Due to massive computational demands of large generative models, AI-Generated Content (AIGC) can organize collaborative Mobile AIGC Service Providers (MASPs) at network edges to provide ubiquitous and customized content generation for resource-constrained users. However, such a paradigm faces two significant challenges: 1) raw prompts (i.e., the task description from users) often lead to poor generation quality due to users' lack of experience with specific AIGC models, and 2) static service provisioning fails to efficiently utilize computational and communication resources given the heterogeneity of AIGC tasks. To address these challenges, we propose an intelligent mobile AIGC service scheme. Firstly, we develop an interactive prompt engineering mechanism that leverages a Large Language Model (LLM) to generate customized prompt corpora and employs Inverse Reinforcement Learning (IRL) for policy imitation through small-scale expert demonstrations. Secondly, we formulate a dynamic mobile AIGC service provisioning problem that jointly optimizes the number of inference trials and transmission power allocation. Then, we propose the Diffusion-Enhanced Deep Deterministic Policy Gradient (D3PG) algorithm to solve the problem. By incorporating the diffusion process into Deep Reinforcement Learning (DRL) architecture, the environment exploration capability can be improved, thus adapting to varying mobile AIGC scenarios. Extensive experimental results demonstrate that our prompt engineering approach improves single-round generation success probability by 6.3 times, while D3PG increases the user service experience by 67.8% compared to baseline DRL approaches.