With the emergence of AI-agent communication networks (ACN) in the 6G era, the efficient training of agents for complex reasoning tasks has become a critical capability for scalable ACN deployment. As a representative complex reasoning task, retrieval-augmented multi-hop question answering (e.g., agentic retrieval-augmented generation) requires agents to perform multi-step reasoning through reflection, planning, and tool-use mechanisms. However, reinforcement learning training still faces reward sparsity and sample efficiency challenges, limiting agents’ rapid evolution and adaptability. We propose dynamic batch-aware advantage weighting (DB-AW), integrating two core components at the batch level: the difficulty-aware weighting component dynamically amplifies positive advantages based on long-term success rates, directing learning toward learnable yet challenging samples; and the batch filtering component removes zero-variance groups, ensuring each update contains non-zero gradient signals. Experiments show that DB-AW achieves 18%, 17%, and 15% relative improvements on Qwen2.5-7B, Qwen2.5-3B, and LLaMA3.2-3B, respectively, while improving the effective update rate from 68% to 100%, significantly reducing agent training costs. As a lightweight and reusable algorithmic module, DB-AW can be readily integrated into methods such as group relative policy optimization (GRPO), providing a practical pathway for efficient training of complex reasoning agents in ACN.

Deep neural networks (DNN) are widely used in image recognition, image classification, and other fields. However, as the model size increases, the DNN hardware accelerators face the challenge of higher area overhead and energy consumption. In recent years, stochastic computing (SC) has been considered a way to realize deep neural networks and reduce hardware consumption. A probabilistic compensation algorithm is proposed to solve the accuracy problem of stochastic calculation, and a fully parallel neural network accelerator based on a deterministic method is designed. The software simulation results show that the accuracy of the probability compensation algorithm on the CIFAR-10 data set is 95.32%, which is 14.98% higher than that of the traditional SC algorithm. The accuracy of the deterministic algorithm on the CIFAR-10 dataset is 95.06%, which is 14.72% higher than that of the traditional SC algorithm. The results of Very Large Scale Integration Circuit (VLSI) hardware tests show that the normalized energy efficiency of the fully parallel neural network accelerator based on the deterministic method is improved by 31% compared with the circuit based on binary computing.

Carrier Ethernet (CE ) is gradually stepping away from standardization and testing to deployment and application in live networks. Although great improvement has been made in the reliability of various CE technologies, there is need for improvement in their Quality of Service (QoS ), Operation, Administration and Maintenance (OAM ), especially the multi-vendor interoperability. The deployment of CE should be service-oriented, and the factors, such as maturity of related technologies and standards, deployment costs, and the complexity of network reconstruction as well as the interoperability with other vendors, should be taken into full consideration to flexibly select appropriate networking technology for different application scenarios according to technical features.