# A-MADiff: Attention-Guided Multi-Agent DRL with Diffusion Policies for Memory-Aware Task Orchestration in Mobile AIGC Networks

arXiv: https://arxiv.org/abs/2608.29255 · HTML: https://mlsanity.com/paper/2608.29255/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning](https://mlsanity.com/paper/2208.06193/) (2022)
- [Actor-Attention-Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1810.02912/) (2018)
- [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024)
- [vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention](https://mlsanity.com/paper/2405.04437/) (2024)
- [Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services](https://mlsanity.com/paper/2303.16129/) (2023)
- [MADiff: Offline Multi-agent Learning with Diffusion Models](https://mlsanity.com/paper/2305.17330/) (2023)
- [Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization](https://mlsanity.com/paper/2308.05384/) (2023)
- [LLM Inference Serving: Survey of Recent Advances and Opportunities](https://mlsanity.com/paper/2407.12391/) (2024)
- [Diffusion-based Reinforcement Learning for Edge-enabled AI-Generated Content Services](https://mlsanity.com/paper/2303.13052/) (2023)
- [Diffusion Model-based Incentive Mechanism with Prospect Theory for Edge AIGC Services in 6G IoT](https://mlsanity.com/paper/2407.10979/) (2024)
- [Resource-efficient Generative Mobile Edge Networks in 6G Era: Fundamentals, Framework and Case Study](https://mlsanity.com/paper/2312.12063/) (2023)
- [Optimizing Resource Allocation for Multi-modal Semantic Communication in Mobile AIGC Networks: A Diffusion-based Game Approach](https://mlsanity.com/paper/2409.17506/) (2024)
- [HybridRAG-based LLM Agents for Low-Carbon Optimization in Low-Altitude Economy Networks](https://mlsanity.com/paper/2506.15947/) (2025)
- [Multi-Agent RL-Based Industrial AIGC Service Offloading over Wireless Edge Networks](https://mlsanity.com/paper/2405.02972/) (2024)
- [Diffusion-based Dynamic Contract for Federated AI Agent Construction in Mobile Metaverses](https://mlsanity.com/paper/2504.14326/) (2025)
- [Transformer based Collaborative Reinforcement Learning for Fluid Antenna System (FAS)-enabled 3D UAV Positioning](https://mlsanity.com/paper/2507.09094/) (2025)
- [EAT: QoS-Aware Edge-Collaborative AIGC Task Scheduling via Attention-Guided Diffusion Reinforcement Learning](https://mlsanity.com/paper/2507.10026/) (2025)
- [Impatient Queuing for Intelligent Task Offloading in Multi-Access Edge Computing](https://mlsanity.com/paper/2105.11727/) (2021)
- [Recursive Offloading for LLM Serving in Multi-tier Networks](https://mlsanity.com/paper/2505.16502/) (2025)

## Abstract (arXiv)

Artificial Intelligence-Generated Content (AIGC) services employ Generative AI (GenAI) models to automatically generate diverse content. Mobile AIGC networks host GenAI models on edge-located AIGC Service Providers (ASPs) to deliver low-latency and personalized AIGC services for mobile users. However, AIGC inference tasks typically occupy GPU memory until task completion, causing GPU memory exhaustion at serving ASPs and triggering out-of-memory failures rather than merely increasing service latency. Existing studies on AIGC task orchestration have largely overlooked GPU memory feasibility constraints. To address this issue, we develop a cooperative multi-agent orchestration framework, in which each edge node is equipped with a scheduling agent to route tasks to local ASPs or neighboring edge nodes. Since scheduling agents make decisions based only on local observations, while peer offloading couples their resource states and long-term utilities, we formulate the orchestration process as a cooperative Decentralized Partially Observable Markov Decision Process (Dec-POMDP). To solve the Dec-POMDP, we propose an underlineAttention-guided underlineMulti-underlineAgent deep reinforcement learning algorithm with underlineDiffusion policies (A-MADiff) under the centralized training with a decentralized execution paradigm. A-MADiff employs diffusion-based decentralized actors to generate multi-modal preferences over feasible orchestration actions, and an attention-guided centralized critic to estimate per-agent values from cross-agent states under GPU memory heterogeneity. Numerical results demonstrate that A-MADiff significantly improves the cumulative reward over the state-of-the-art baseline.