Related papers: SkillOrchestra: Learning to Route Agents via Skill…

The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively…

As demand for Large Language Models (LLMs) and AI agents grows rapidly, optimizing systems for efficient LLM inference becomes critical. While significant efforts have targeted system-level engineering, little has been explored from a…

The architecture of Transformer is based entirely on self-attention, and has been shown to outperform models that employ recurrence on sequence transduction tasks such as machine translation. The superior performance of Transformer has been…

Efficiently scheduling data processing jobs on distributed compute clusters requires complex algorithms. Current systems, however, use simple generalized heuristics and ignore workload characteristics, since developing and tuning a…

A key functionality of emerging connected autonomous systems such as smart transportation systems, smart cities, and the industrial Internet-of-Things, is the ability to process and learn from data collected at different physical locations.…

Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, high-quality skills are still largely written by hand. We introduce SkillGen, a…

We present an agentic AI framework for autonomous multimodal query processing that coordinates specialized tools across text, image, audio, video, and document modalities. A central Supervisor dynamically decomposes user queries, delegates…

The surge in generative AI workloads has created a need for scalable inference systems that can flexibly harness both GPUs and specialized accelerators while containing operational costs. This paper proposes a hardware-agnostic control loop…

In collaborative human-robot order picking systems, human pickers and Autonomous Mobile Robots (AMRs) travel independently through a warehouse and meet at pick locations where pickers load items onto the AMRs. In this paper, we consider an…

The transport capacity of a communication network can be characterized by the transition from a free-flow state to a congested state. Here, we propose a dynamic routing strategy in complex networks based on hierarchical bypass selections.…

The proliferation of large language models (LLMs) with varying computational costs and performance profiles presents a critical challenge for scalable, cost-effective deployment in real-world applications. We introduce a unified routing…

Network slicing is a crucial enabler and a trend for the Next Generation Mobile Network (NGMN) and various other new systems like the Internet of Vehicles (IoV) and Industrial IoT (IIoT). Orchestration and machine learning are key elements…

Adopting serverless computing to edge networks benefits end-users from the pay-as-you-use billing model and flexible scaling of applications. This paradigm extends the boundaries of edge computing and remarkably improves the quality of…

Multi-agent large language model (LLM) systems have shown strong potential in complex reasoning and collaborative decision-making tasks. However, most existing coordination schemes rely on static or full-context routing strategies, which…

Training a team of agents from scratch in multi-agent reinforcement learning (MARL) is highly inefficient, much like asking beginners to play a symphony together without first practicing solo. Existing methods, such as offline or…

The need for autonomous robot systems in both the service and the industrial domain is larger than ever. In the latter, the transition to small batches or even "batch size 1" in production created a need for robot control system…

Large language models (LLMs) demonstrate remarkable performance across diverse tasks, yet their effectiveness frequently depends on costly commercial APIs or cloud services. Model selection thus entails a critical trade-off between…

Compositional spatiotemporal reasoning often requires a system to invoke multiple heterogeneous specialists, such as geometric, temporal, topological, and trajectory agents. A central question is how such a system should route among…

Current networks more and more rely on virtualized middleboxes to flexibly provide security, protocol optimization, and policy compliance functionalities. As such, delivering these services requires that the traffic be steered through the…

Mixture-of-Agents (MoA) improves LLM performance through layered collaboration, but its dense topology raises costs and latency. Existing methods employ LLM judges to filter responses, yet still require all models to perform inference…