# Multi-Agent Transformer for Queue-Level XR Traffic Scheduling in TSN Networks

arXiv: https://arxiv.org/abs/2608.05340 · HTML: https://mlsanity.com/paper/2608.05340/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 9 of 9)

- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2109.11251/) (2021)
- [Multi-Agent Reinforcement Learning is a Sequence Modeling Problem](https://mlsanity.com/paper/2205.14953/) (2022)
- [Semantic Communications in Networked Systems: A Data Significance Perspective](https://mlsanity.com/paper/2103.05391/) (2021)
- [An eXtended Reality Offloading IP Traffic Dataset and Models](https://mlsanity.com/paper/2301.11217/) (2023)
- [Edge Learning via Federated Split Decision Transformers for Metaverse Resource Allocation](https://mlsanity.com/paper/2602.16174/) (2026)
- [A Survey of Scheduling Algorithms for the Time-Aware Shaper in Time-Sensitive Networking (TSN)](https://mlsanity.com/paper/2211.10954/) (2022)
- [PDU-set Scheduling Algorithm for XR Traffic in Multi-Service 5G-Advanced Networks](https://mlsanity.com/paper/2311.08969/) (2023)
- [Self-Play Ensemble Q-learning enabled Resource Allocation for Network Slicing](https://mlsanity.com/paper/2408.10376/) (2024)

## Abstract (arXiv)

Time-Sensitive Networking (TSN) and Mobile Edge Computing (MEC) hold strong potential for enabling ultra-reliable low-latency communication for time-sensitive applications, such as eXtended Reality (XR). However, the widespread adoption of XR introduces significant challenges due to co-located services in MEC environments, leading to contention for shared network resources. Moreover, XR traffic types have distinct characteristics and criticality in terms of timing requirements, further increasing the complexity and dynamics of such environments. Although reinforcement learning has shown promise for TSN scheduling optimization in dynamic network scenarios, existing approaches rely on centralized or high-level multi-agent designs and are typically tailored to periodic and predictable industrial traffic, limiting their applicability to XR workloads. As a result, these approaches suffer from (i) limited ability to capture inter-queue dependencies due to coarse-grained control, and (ii) poor adaptability to highly dynamic and heterogeneous XR traffic. To address these gaps, we propose a multi-agent reinforcement learning approach for queue-level XR traffic scheduling. We adopt the multi-agent transformer (MAT) to model inter-queue dependencies via attention over agents' observations and actions, enabling implicit coordination across heterogeneous co-located XR applications. Our simulation results show that the proposed method outperforms baselines, achieving up to 71.42% latency reduction and up to 83.2% reduction in failure rate, while consistently achieving high reliability across all queues.