XAI-Guided Conservative Decentralized Execution for Offline Multi-Agent Network Slicing

Eslam Eldeeb; Hatim Chergui; Merouane Debbah

cs.MAAug 14, 2026

XAI-Guided Conservative Decentralized Execution for Offline Multi-Agent Network Slicing

Authors: Eslam Eldeeb, Hatim Chergui, Merouane Debbah

Organizations: Centre for Wireless Communications (CWC), University of Oulu, Finland · i2CAT Foundation, Spain · Research Institute for Digital Future, Khalifa University, 127788 Abu Dhabi, UAE

Abstract

The recent advances toward sixth-generation (6G) and beyond-6G networks have accelerated the need for intelligent resource management mechanisms capable of supporting heterogeneous services under shared infrastructures in network slicing. However, resource allocation in network slicing naturally forms a resource-coupled cooperative optimization problem with competing slice demands. Slices compete for limited resources to minimize individual latencies while coordinating to avoid conflicts and underutilization. Although multi-agent reinforcement learning (MARL) has shown promising performance in such settings, existing online formulations remain costly, unsafe, and difficult to deploy due to their reliance on environmental interactions and communication among agents. In this work, we present explainable artificial intelligence (XAI)-guided conservative decentralized execution (X-CODE). X-CODE is an explainable offline MARL that operates offline without environmental interaction, nor inter-agent communication. It exploits explainability-aware reward shaping to modify the relative preference among joint offline transitions during centralized training to improve decentralized resource-allocation behavior. In deployment, the agents operate independently without signaling exchange among the agents. Simulation results demonstrate that the proposed approach achieves zero observed resource-conflict events in the evaluated test episodes while minimizing per-slice latencies. Moreover, the proposed framework exhibits lower signaling overhead and reduces effective inference latency by 88 % under the considered communication-delay model compared to the online baselines. Source codes and datasets are available through: https://github.com/Eslam211/xcode-ran-slicing.

Figures & tables

Fig. 1: A diagram illustrating the proposed X-CODE Algorithm. An offline dataset and pretrained VDN Q-networks are used to perform reward shaping and construct the explainable dataset. Then, the proposed X-CODE training is performed via value-decomposed CQL-VDN training. Finally, coordinated agents execute their learned policies online without any inter-agent communication.

Panel of Figure 2 — Fig. 2: Performance of online training compared to the heuristic baseline in terms of: (a) per-step reward, (b) average latency, and (c) conflict rate.

Parameter	Value	Parameter	Value
$K$	$3$	$T$	$40$
$f_{\text{max}}$	$40$	$f_{\mathrm{th}}$	$[15,15,10]$ Gcycles/s
$\tau$	$0.01$ s	$U$	$5\times 10^{-3}$ bits/cycle
$\alpha$	$1$	$\mu$	$1$
$\lambda_{c}$	$30$	$\lambda_{l}$	$150$
$\lambda_{a}$	$0.05$	Replay buffer	$10,000$

TABLE I: Simulation parameters and hyperparameters

Panel of Figure 4 — Fig. 3: A comparison of the action coverage of datasets collected during training the online baselines compared to the uniform random-walk dataset.

Panel of Figure 5 — Fig. 4: The performance of the proposed X-CODE compared to the baselines in terms of the latency and conflict CDFs, respectively.

Panel of Figure 6 — Fig. 5: The performance of the proposed X-CODE compared to MARL baselines in terms of the latency CDF and the CPU utilization.

Panel of Figure 7 — Fig. 6: The performance of the proposed X-CODE while sweeping: (a) CQL parameter $\alpha$ , and (b) explainability strength $\mu$ .

Panel of Figure 8 — Fig. 7: The attribution of each feature to the predictions represented in terms of the KDE plot and SHAP values.

Panel of Figure 9 — Fig. 8: The complexity analysis of the proposed X-CODE compared to the DQN (Comm + IB) in terms of the signaling overhead and the inference time under the considered delay model.

Network Slicing

See all 14 papers

Privacy-Aware Agent Collaboration for Dynamic VR Slice Management in 6G SD-RAN
May 28, 2026Khaled M. Naguib, Soumaya Cherkaoui, Mahmoud M. Elmesalawy +26G Networks Wireless Communications
Department of Computer and Software Engineering, Polytechnique Montr´eal, Montr´eal, Canada · Electronics and Communications, Helwan Univ. Cairo, Egypt
Adversarial Attacks in AI-Driven RAN Slicing: SLA Violations and Recovery
Apr 1, 2026Deemah H. Tashman, Soumaya CherkaouiAdversarial Attacks Network Slicing
Department of Computer and Software Engineering, Polytechnique Montreal, Montreal, Canada
Optimization-as-a-Service via Multi-Agent Large Language Model for Radio Access Networks
May 15, 2026Chaoqun You, Yueyue Dai, Xingqiu He +3Multi-Agent System Optimization Large Language Model-Guided Optimization
Fudan University · Huazhong University of Science and Technology · University of Surrey +1

May 28, 2026J/K move · Enter open · S save

Privacy-Aware Agent Collaboration for Dynamic VR Slice Management in 6G SD-RAN

Khaled M. Naguib, Soumaya Cherkaoui, Mahmoud M. Elmesalawy, Ahmed M. Abd El-Haleem+1

Department of Computer and Software Engineering, Polytechnique Montr´eal, Montr´eal, Canada · Electronics and Communications, Helwan Univ. Cairo, Egypt

6G Networks Wireless Communications Wireless Resource Allocation Cooperative MARL Multi-Agent Reinforcement Learning

Open paper AskPDF arXiv

Ultra-low latency and high throughput are required for Virtual Reality (VR) services in 6G networks, which presents critical challenges for Software-Defined Radio Access Networks (SD-RANs) dynamic resource management. This work propose a mobility-driven, privacy-aware Multi-Agent Reinforcement Learning (MARL) framework for VR slice management, in which cooperative agents maximize resource distribution over end-to-end VR links while protecting the privacy of user data. Our approach incorporates mobility prediction and an information bottleneck encoder to facilitate effective and secure agent collaboration. In simulations, comparisons with traditional methods are studied which show up to 34% throughput improvement, 28% fewer resources, and 85% less privacy leakage, guaranteeing dependable immersive VR experiences in future 6G environments.

Abstract

Network Slicing

Explore similar work

Privacy-Aware Agent Collaboration for Dynamic VR Slice Management in 6G SD-RAN

Adversarial Attacks in AI-Driven RAN Slicing: SLA Violations and Recovery

Optimization-as-a-Service via Multi-Agent Large Language Model for Radio Access Networks