Related papers: Interpretable Attention-Based Multi-Agent PPO for …
Network slicing enables the operator to configure virtual network instances for diverse services with specific requirements. To achieve the slice-aware radio resource scheduling, dynamic slicing resource partitioning is needed to…
Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data, but they often struggle with complex reasoning. While Reinforcement learning (RL) can boost reasoning in LLMs, applying it to MLLMs is tricky. Common issues…
Enhancing LLMs with the ability to actively search external knowledge is crucial for complex and real-world tasks. Current approaches either rely on prompting to elicit the model's innate agent capabilities, or suffer from performance…
The deployment of large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy. However, it is critically challenged by the resource constraints of a single edge node.…
Adaptivity, reconfigurability and intelligence are key features of the next-generation wireless networks to meet the increasingly diverse quality of service (QoS) requirements of the future applications. Conventional protocol designs,…
Artificial intelligence approaches for base-band processing for radio receivers have demonstrated significant performance gains. Most of the proposed methods are characterized by high compute and memory requirements, hindering their…
The rapid advancement of Low-Power Wide Area Networks (LPWANs), particularly Long Range (LoRa) systems, has positioned them as a cornerstone for Next-Generation Internet of Things (NG-IoT) applications within 5G/6G ecosystems. Despite their…
Artificial intelligence (AI) is expected to significantly enhance radio resource management (RRM) in sixth-generation (6G) networks. However, the lack of explainability in complex deep learning (DL) models poses a challenge for practical…
There is a broad consensus that artificial intelligence (AI) will be a defining component of the sixth-generation (6G) networks. As a specific instance, AI-empowered sensing will gather and process environmental perception data at the…
Safety in reinforcement learning (RL) is typically enforced through objective shaping while keeping environment dynamics stationary with respect to observable state-action pairs. Under delayed harm, this can lead to replay: after a washout…
Unmanned aerial vehicles serving as aerial base stations can rapidly restore connectivity after disasters, yet abrupt changes in user mobility and traffic demands shift the quality of service trade-offs and induce strong non-stationarity.…
Deep Reinforcement Learning (DRL) has emerged as a powerful solution for meeting the growing demands for connectivity, reliability, low latency and operational efficiency in advanced networks. However, most research has focused on…
We propose Multi Agent Reflective Policy Optimization (MARPO) to alleviate the issue of sample inefficiency in multi agent reinforcement learning. MARPO consists of two key components: a reflection mechanism that leverages subsequent…
With the rapid deployment of the Internet of Things (IoT), fifth-generation (5G) and beyond 5G networks are required to support massive access of a huge number of devices over limited radio spectrum radio. In wireless networks, different…
In this paper, we propose an Agentic Artificial Intelligence (AI) framework for wireless networks. The framework coordinates a pool of AI agents guided by Natural Language (NL) inputs from a human operator. At its core, the super agent is…
Artificial intelligence (AI)-driven zero-touch network slicing (NS) is a new paradigm enabling the automation of resource management and orchestration (MANO) in multi-tenant beyond 5G (B5G) networks. In this paper, we tackle the problem of…
Traditional AI alignment primarily focuses on individual model outputs; however, autonomous agents in long-horizon workflows require sustained reliability across entire interaction trajectories. We introduce APEMO (Affect-aware Peak-End…
Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for downstream alignment. Existing trajectory-based RL…
Large language models (LLMs) typically operate in a question-answering paradigm, where the quality of the input prompt critically affects the response. Automated Prompt Optimization (APO) aims to overcome the cognitive biases of manually…
Since DeepSeek-R1 popularized, Group Relative Policy Optimization (GRPO) has become the core part of training Reasoning LLMs. However, we find some deficiency that influences RL stability and inference efficiency, like zero-variance in…