While existing DML attempts have made significant progress, two technical barriers remain in realistic scenarios.

The deployment of Unmanned Aerial Vehicle (UAV) swarms as dynamic communication relays is critical for next-generation tactical networks. However, operating in contested environments requires solving a complex trade-off, including maximizing system throughput while ensuring collision avoidance and resilience against adversarial jamming. Existing heuristic-based approaches often struggle to find effective solutions due to the dynamic and multi-objective nature of this problem. This paper formulates this challenge as a cooperative Multi-Agent Reinforcement Learning (MARL) problem, solved using the Centralized Training with Decentralized Execution (CTDE) framework. Our approach employs a centralized critic that uses global state information to guide decentralized actors which operate using only local observations. Simulation results show that our proposed framework significantly outperforms heuristic baselines, increasing the total system throughput by approximately 50% while simultaneously achieving a near-zero collision rate. A key finding is that the agents develop an emergent anti-jamming strategy without explicit programming. They learn to intelligently position themselves to balance the trade-off between mitigating interference from jammers and maintaining effective communication links with ground users.

Ensuring packet-level communication quality is vital for ultra-reliable, low-latency communications (URLLC) in large-scale industrial wireless networks. We enhance the Local Deadline Partition (LDP) algorithm by introducing a CNN-based dynamic priority prediction mechanism for improved interference coordination in multi-cell, multi-channel networks. Unlike LDP's static priorities, our approach uses a Convolutional Neural Network and graph coloring to adaptively assign link priorities based on real-time traffic, transmission opportunities, and network conditions. Assuming that first training phase is performed offline, our approach introduced minimal overhead, while enabling more efficient resource allocation, boosting network capacity, SINR, and schedulability. Simulation results show SINR gains of up to 113\%, 94\%, and 49\% over LDP across three network configurations, highlighting its effectiveness for complex URLLC scenarios.

--Networks built on the IEEE 802.11 standard have experienced rapid growth in the last decade. Their field of application is vast, including smart home applications, Internet of Things (IoT), and short-range high throughput static and dynamic inter-vehicular communication networks. Within such networks, Channel State Information (CSI) provides a detailed view of the state of the communication channel and represents the combined effects of multipath propagation, scattering, phase shift, fading, and power decay. In this work, we investigate the problem of jamming attack detection in static and dynamic vehicular networks. We utilize ESP32-S3 modules to set up a communication network between an Unmanned Aerial V ehicle (UA V) and a Ground Control Station (GCS), to experimentally test the combined effects of a constant jammer on recorded CSI parameters, and the feasibility of jamming detection through CSI analysis in static and dynamic communication scenarios. The rapid expansion of IEEE 802.11 networks over the past decade has revolutionized wireless communications, particularly in such applications as smart homes [1], Internet of Things (IoT) [2], industrial automation, and short-range high-throughput vehicular networks [3]. This can be contributed to their high throughput capabilities, ease of deployment, and increasingly growing demand for internet connectivity. However, the widespread usage and extensive deployment of these networks make them an attractive target for malicious actors, and thus, more exposed and susceptible to jamming attacks.

Abstract-- We present a fully decentralized routing framework for multi-robot exploration missions operating under the constraints of a Lunar Delay-T olerant Network (LDTN). In this setting, autonomous rovers must relay collected data to a lander under intermittent connectivity and unknown mobility patterns. We formulate the problem as a Partially Observable Markov Decision Problem (POMDP) and propose a Graph Attention-based Multi-Agent Reinforcement Learning (GA T - MARL) policy that performs Centralized Training, Decentralized Execution (CTDE). Our method relies only on local observations and does not require global topology updates or packet replication, unlike classical approaches such as shortest path and controlled flooding-based algorithms. Through Monte Carlo simulations in randomized exploration environments, GA T -MARL provides higher delivery rates, no duplications, and fewer packet losses, and is able to leverage short-term mobility forecasts; offering a scalable solution for future space robotic systems for planetary exploration, as demonstrated by successful generalization to larger rover teams. The renewed interest in planetary and lunar surface exploration has accelerated the development of autonomous multi-robot systems.

Large Language Model-based Multi-Agent Systems (MASs) have emerged as a powerful paradigm for tackling complex tasks through collaborative intelligence. However, the topology of these systems--how agents in MASs should be configured, connected, and coordinated--remains largely unexplored. In this position paper, we call for a paradigm shift toward \emph{topology-aware MASs} that explicitly model and dynamically optimize the structure of inter-agent interactions. We identify three fundamental components--agents, communication links, and overall topology--that collectively determine the system's adaptability, efficiency, robustness, and fairness. To operationalize this vision, we introduce a systematic three-stage framework: 1) agent selection, 2) structure profiling, and 3) topology synthesis. This framework not only provides a principled foundation for designing MASs but also opens new research frontiers across language modeling, reinforcement learning, graph learning, and generative modeling to ultimately unleash their full potential in complex real-world applications. We conclude by outlining key challenges and opportunities in MASs evaluation. We hope our framework and perspectives offer critical new insights in the era of agentic AI.

Long-context large language models (LLMs) face constraints due to the quadratic complexity of the self-attention mechanism. The mainstream sequence parallelism (SP) method, Ring Attention, attempts to solve this by distributing the query into multiple query chunks across accelerators and enable each Q tensor to access all KV tensors from other accelerators via the Ring AllGather communication primitive. However, it exhibits low communication efficiency, restricting its practical applicability. This inefficiency stems from the mismatch between the Ring AllGather communication primitive it adopts and the AlltoAll topology of modern accelerators. A Ring AllGather primitive is composed of iterations of ring-styled data transfer, which can only utilize a very limited fraction of an AlltoAll topology. Inspired by the Hamiltonian decomposition of complete directed graphs, we identify that modern accelerator topology can be decomposed into multiple orthogonal ring datapaths which can concurrently transfer data without interference. Based on this, we further observe that the Ring AllGather primitive can also be decomposed into the same number of concurrent ring-styled data transfer at every iteration. Based on these insights, we propose TASP, a topology-aware SP method for long-context LLMs that fully utilizes the communication capacity of modern accelerators via topology decomposition and primitive decomposition. Experimental results on both single-node and multi-node NVIDIA H100 systems and a single-node AMD MI300X system demonstrate that TASP achieves higher communication efficiency than Ring Attention on these modern accelerator topologies and achieves up to 3.58 speedup than Ring Attention and its variant Zigzag-Ring Attention. The code is available at https://github.com/infinigence/HamiltonAttention.

Figure 1: Left: A scenario in which two agents speak different languages to describe the same object.

Federated learning (FL) has emerged as a promising paradigm within edge computing (EC) systems, enabling numerous edge devices to collaboratively train artificial intelligence (AI) models while maintaining data privacy. To overcome the communication bottlenecks associated with centralized parameter servers, decentralized federated learning (DFL), which leverages peer-to-peer (P2P) communication, has been extensively explored in the research community. Although researchers design a variety of DFL approach to ensure model convergence, its iterative learning process inevitably incurs considerable cost along with the growth of model complexity and the number of participants. These costs are largely influenced by the dynamic changes of topology in each training round, particularly its sparsity and connectivity conditions. Furthermore, the inherent resources heterogeneity in the edge environments affects energy efficiency of learning process, while data heterogeneity degrades model performance. These factors pose significant challenges to the design of an effective DFL framework for EC systems. To this end, we propose Hat-DFed, a heterogeneity-aware and coset-effective decentralized federated learning (DFL) framework. In Hat-DFed, the topology construction is formulated as a dual optimization problem, which is then proven to be NP-hard, with the goal of maximizing model performance while minimizing cumulative energy consumption in complex edge environments. To solve this problem, we design a two-phase algorithm that dynamically constructs optimal communication topologies while unbiasedly estimating their impact on both model performance and energy cost. Additionally, the algorithm incorporates an importance-aware model aggregation mechanism to mitigate performance degradation caused by data heterogeneity.