Related papers: RollArt: Scaling Agentic RL Training via Disaggreg…

Effective cross-functional coordination is essential for enhancing firm-wide profitability, particularly in the face of growing organizational complexity and scale. Recent advances in artificial intelligence, especially in reinforcement…

Agentic reinforcement learning (RL) is reshaping LLM post-training, but end-to-end training time is dominated by compute-intensive, multi-turn rollouts whose resource demand varies significantly across training steps. Resource-fixed systems…

Maximizing training throughput and cost-efficiency of RL for LLMs is essential to democratize this advanced technique. One promising but challenging approach is to deploy such a computational workflow over heterogeneous GPUs. Unlike…

Reinforcement Learning (RL) has become the most effective post-training approach for improving the capabilities of Large Language Models (LLMs). In practice, because of the high demands on latency and memory, it is particularly challenging…

Disaggregating the generation and training stages in RL is widely adopted to scale LLM post-training. There are two critical challenges here. First, the generation stage often becomes a bottleneck due to dynamic workload shifts and severe…

Reinforcement learning (RL) has become essential for unlocking advanced reasoning capabilities in large language models (LLMs). RL workflows involve interleaving rollout and training stages with fundamentally different resource…

Resource-disaggregated data centres (RDDC) propose a resource-centric, and high-utilisation architecture for data centres (DC), avoiding resource fragmentation and enabling arbitrarily sized resource pools to be allocated to tasks, rather…

We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or…

Ultra-reliable low latency communications (URLLC) service is envisioned to enable use cases with strict reliability and latency requirements in 5G. One approach for enabling URLLC services is to leverage Reinforcement Learning (RL) to…

Resource allocation in integrated sensing and communication (ISAC) systems needs to be optimized to balance the requirements of the communication and sensing modules considering complicated cross-layer data traffic and queue status in…

In this paper, we introduce Quantum-Train-Based Distributed Multi-Agent Reinforcement Learning (Dist-QTRL), a novel approach to addressing the scalability challenges of traditional Reinforcement Learning (RL) by integrating quantum…

Adaptive Mixed-Criticality (AMC) is a fixed-priority preemptive scheduling algorithm for mixed-criticality hard real-time systems. It dominates many other scheduling algorithms for mixed-criticality systems, but does so at the cost of…

Reinforcement learning (RL) is central to post-training, particularly for agentic models that require specialized reasoning behaviors. In this setting, model merging offers a practical mechanism for integrating multiple RL-trained agents…

Reinforcement learning (RL) is currently used in various real-life applications. RL-based solutions have the potential to generically address problems, including the ones that are difficult to solve with heuristics and meta-heuristics and,…

Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as…

As emerging networks such as Open Radio Access Networks (O-RAN) and 5G continue to grow, the demand for various services with different requirements is increasing. Network slicing has emerged as a potential solution to address the different…

Scalability is the key roadstone towards the application of cooperative intelligent algorithms in large-scale networks. Reinforcement learning (RL) is known as model-free and high efficient intelligent algorithm for communication problems…

Language model (LM) agents have gained significant attention for their ability to autonomously complete tasks through interactions with environments, tools, and APIs. LM agents are primarily built with prompt engineering or supervised…

We introduce OpenTinker, an infrastructure for reinforcement learning (RL) of large language model (LLM) agents built around a separation of concerns across algorithm design, execution, and agent-environment interaction. Rather than relying…

Efficient load balancing is crucial in cloud computing environments to ensure optimal resource utilization, minimize response times, and prevent server overload. Traditional load balancing algorithms, such as round-robin or least…