# Fine-Grained AI Model Caching and Downloading With Coordinated Multipoint Broadcasting in Multi-Cell Edge Networks

arXiv: https://arxiv.org/abs/2509.19341 · HTML: https://mlsanity.com/paper/2509.19341/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Builds on (most cited first, 22 of 22)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [A Theoretical Analysis of Deep Q-Learning](https://mlsanity.com/paper/1901.00137/) (2019)
- [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024)
- [Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications](https://mlsanity.com/paper/1812.11794/) (2018)
- [OpenELM: An Efficient Language Model Family with Open Training and Inference Framework](https://mlsanity.com/paper/2404.14619/) (2024)
- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [Action Semantics Network: Considering the Effects of Actions in Multiagent Systems](https://mlsanity.com/paper/1907.11461/) (2019)
- [Optimal Model Placement and Online Model Splitting for Device-Edge Co-Inference](https://mlsanity.com/paper/2105.13618/) (2021)
- [DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference](https://mlsanity.com/paper/2306.01811/) (2023)
- [Rethinking Resource Management in Edge Learning: A Joint Pre-training and Fine-tuning Design Paradigm](https://mlsanity.com/paper/2404.00836/) (2024)
- [TrimCaching: Parameter-sharing AI Model Caching in Wireless Edge Networks](https://mlsanity.com/paper/2405.03990/) (2024)
- [SplitPlace: AI Augmented Splitting and Placement of Large-Scale Neural Networks in Mobile Edge Environments](https://mlsanity.com/paper/2205.10635/) (2022)
- [Energy-Efficient Processing and Robust Wireless Cooperative Transmission for Edge Inference](https://mlsanity.com/paper/1907.12475/) (2019)
- [In-situ Model Downloading to Realize Versatile Edge AI in 6G Mobile Networks](https://mlsanity.com/paper/2210.03555/) (2022)
- [Efficient Multiuser AI Downloading via Reusable Knowledge Broadcasting](https://mlsanity.com/paper/2307.15316/) (2023)
- [Resource Management for Low-latency Cooperative Fine-tuning of Foundation Models at the Network Edge](https://mlsanity.com/paper/2407.09873/) (2024)
- [Resource Allocation for Simultaneous Wireless Information and Power Transfer Systems: A Tutorial Overview](https://mlsanity.com/paper/2110.07296/) (2021)
- [Cooperative Hybrid Transmit Beamforming in Cell-free mmWave MIMO Networks](https://mlsanity.com/paper/2212.07318/) (2022)
- [Precoding for Multi-Cell ISAC: from Coordinated Beamforming to Coordinated Multipoint and Bi-Static Sensing](https://mlsanity.com/paper/2402.18387/) (2024)

## Abstract (arXiv)

6G networks are envisioned to support on-demand AI model downloading to accommodate diverse inference requirements of end users. By proactively caching models at edge nodes, users can retrieve the requested models with low latency for on-device AI inference. However, the substantial size of contemporary AI models poses significant challenges for edge caching under limited storage capacity, as well as for the concurrent delivery of heterogeneous models over wireless channels. To address these challenges, we propose a fine-grained AI model caching and downloading system that exploits parameter reusability, stemming from the common practice of fine-tuning task-specific models from a shared pre-trained model with frozen parameters. This system selectively caches model parameter blocks (PBs) at edge nodes, eliminating redundant storage of reusable parameters across different cached models. Additionally, it incorporates coordinated multipoint (CoMP) broadcasting to simultaneously deliver reusable PBs to multiple users, thereby enhancing downlink spectrum utilization. Under this arrangement, we formulate a model downloading delay minimization problem to jointly optimize PB caching, migration (among edge nodes), and broadcasting beamforming. To tackle this intractable problem, we develop a distributed multi-agent learning framework that enables edge nodes to explicitly learn mutual influence among their actions, thereby facilitating cooperation. Furthermore, a data augmentation approach is proposed to adaptively generate synthetic training samples through a predictive model, boosting sample efficiency and accelerating policy learning. Both theoretical analysis and simulation experiments validate the superior convergence performance of the proposed learning framework.