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

Conventional theoretical machine learning studies generally assume explicitly or implicitly that there are enough or even infinitely supplied computational resources. In real practice, however, computational resources are usually limited,…

Current state-of-the-art large-scale conversational AI or intelligent digital assistant systems in industry comprises a set of components such as Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU). For some of these…

While multi-agent systems (MAS) have demonstrated superior performance over single-agent approaches in complex reasoning tasks, they often suffer from significant computational inefficiencies. Existing frameworks typically deploy large…

The ability to effectively reuse prior knowledge is a key requirement when building general and flexible Reinforcement Learning (RL) agents. Skill reuse is one of the most common approaches, but current methods have considerable…

Multi-agent Retrieval-Augmented Generation (RAG), wherein each agent takes on a specific role, supports hard queries that require multiple steps and sources, or complex reasoning. Existing approaches, however, rely on static agent behaviors…

Practising and honing skills forms a fundamental component of how humans learn, yet artificial agents are rarely specifically trained to perform them. Instead, they are usually trained end-to-end, with the hope being that useful skills will…

Modern communication networks have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this paper, we develop a novel experience-driven approach that can learn to well control a communication…

With the development of LLMs as agents, there is a growing interest in connecting multiple agents into multi-agent systems to solve tasks concurrently, focusing on their role in task assignment and coordination. This paper explores how LLMs…

Evaluating AI agents on comprehensive benchmarks is expensive because each evaluation requires interactive rollouts with tool use and multi-step reasoning. We study whether small task subsets can preserve agent rankings at substantially…

The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new…

We introduce Context Kubernetes, an architecture for orchestrating enterprise knowledge in agentic AI systems, with a prototype implementation and eight experiments. The core observation is that delivering the right knowledge, to the right…

The use of semi-autonomous and autonomous robotic assistants to aid in care of the elderly is expected to ease the burden on human caretakers, with small-stage testing already occurring in a variety of countries. Yet, it is likely that…

This paper is about optimally controlling skill-based queueing systems such as data centers, cloud computing networks, and service systems. By means of a case study using a real-world data set, we investigate the practical implementation of…

As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and…

Today high-performance computing (HPC) platforms are still dominated by batch jobs. Accordingly, effective batch job scheduling is crucial to obtain high system efficiency. Existing HPC batch job schedulers typically leverage heuristic…

Large language model (LLM) agents at the network edge offer low-latency execution for routine queries. In contrast, complex requests often require the superior capability of cloud models, incurring higher latency and cost. To navigate this…

Modern distributed systems demand low-latency, fault-tolerant event processing that exceeds traditional messaging architecture limits. While frameworks including Apache Kafka, RabbitMQ, Apache Pulsar, NATS JetStream, and serverless event…

Driving in dense traffic with human and autonomous drivers is a challenging task that requires high-level planning and reasoning. Human drivers can achieve this task comfortably, and there has been many efforts to model human driver…

LLM routing aims to achieve a favorable quality--cost trade-off by dynamically assigning easy queries to smaller models and harder queries to stronger ones. However, across both unimodal and multimodal settings, we uncover a pervasive yet…

This paper presents ORXE, a modular and adaptable framework for achieving real-time configurable efficiency in AI models. By leveraging a collection of pre-trained experts with diverse computational costs and performance levels, ORXE…