The fast development of Artificial Intelligence (AI) agents provides a promising way for the realization of intelligent and customized wireless networks. In this paper, we propose a Wireless Multi-Agent System (WMAS), which can provide intelligent and customized services for different user equipment (UEs). Note that orchestrating multiple agents carries the risk of malfunction, and multi-agent conversations may fall into infinite loops. It is thus crucial to design a conversation topology for WMAS that enables agents to complete UE task requests with high accuracy and low conversation overhead. To address this issue, we model the multi-agent conversation topology as a directed acyclic graph and propose a reinforcement learning- based algorithm to optimize the adjacency matrix of this graph. As such, WMAS is capable of generating and self-optimizing multi-agent conversation topologies, enabling agents to effectively and collaboratively handle a variety of task requests from UEs. Simulation results across various task types demonstrate that WMAS can achieve higher task performance and lower conversation overhead compared to existing multi-agent systems. These results validate the potential of WMAS to enhance the intelligence of future wireless networks.

In a real-time transmission scenario, messages are transmitted through a channel that is subject to packet loss. The destination must recover the messages within the required deadline. In this paper, we consider a setup where two different types of messages with distinct decoding deadlines are transmitted through a channel model that introduces either one burst erasure of length at most B, or N random erasures in any fixed-sized sliding window. The message with a short decoding deadline$T_{\mathrm {u}}$is referred to as an urgent message, while the other one with a decoding deadline$T_{\mathrm {v}}$($T_{\mathrm {v}} \gt T_{\mathrm {u}}$) is referred to as a less urgent message. We consider the scenario where$T_{\mathrm {v}} \gt T_{\mathrm {u}} + B$and propose a non-trivial achievable region$\mathcal {R}$for the aforementioned channel model. We propose a novel merging approach to encode two message streams of different urgency levels into a single flow and present explicit constructions for encoding, contributing to the establishment of the achievability of region$\mathcal {R}$. Our comprehensive analysis demonstrates that this region encompasses the rate pairs of existing encoding schemes and coincides with the capacity region in burst channel scenarios. Lastly, we investigate the property of the achievable region$\mathcal {R}$, proving that it is the largest one obtained from all the rate pairs under the merging method.

This letter addresses the challenge of multiplying large real-numbered matrices$\mathbf {A}$and$\mathbf {B}$in on-device edge computing environments with a master node and$N$worker nodes. To ensure accuracy and mitigate adversarial behavior, existing approaches rely on polynomial coding techniques. However, polynomial decoding on real numbers is numerically unstable, leading prior works to employ finite fields or complex number fields. Nevertheless, computing on finite fields may encounter computation overflows. In this letter, we propose a novel, numerically stable coded matrix multiplication scheme on real number fields. Our approach detects malicious workers and mitigates the impact of slower workers (stragglers), all while operating solely on real number fields.