Related papers: CALM: A Self-Adaptive Orchestration Approach for Q…

Large language models (LLMs) rely on Key-Value (KV) cache to reduce time-to-first-token (TTFT) latency, but existing disk-based KV cache systems using file-per-object layouts suffer from severe scalability bottlenecks due to file system…

In autonomic computing, self-adaptation has been proposed as a fundamental paradigm to manage the complexity of multiagent systems (MASs). This achieved by extending a system with support to monitor and adapt itself to achieve specific…

Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to…

As modern artificial intelligence (AI) systems become more advanced and capable, they can leverage a wide range of tools and models to perform complex tasks. The task of orchestrating these models is increasingly performed by Large Language…

Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While prior systems optimize throughput and latency by batching, scheduling, and…

LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the…

Model-as-a-Service (MaaS) platforms face diverse Service Level Objective (SLO) requirements stemming from various large language model (LLM) applications, manifested in contextual complexity, first-token latency, and between-token latency.…

Large language models (LLMs) are increasingly being explored as high-level decision modules in closed-loop systems, but their stochastic nature makes safe integration challenging. In this paper, we propose LLM-Steered Power Allocation, a…

Large Language Models (LLMs) possess remarkable generalization capabilities but struggle with multi-task adaptation, particularly in balancing knowledge retention with task-specific specialization. Conventional fine-tuning methods suffer…

Tackling complex optimization problems often relies on expert-designed heuristics, typically crafted through extensive trial and error. Recent advances demonstrate that large language models (LLMs), when integrated into well-designed…

Being more powerful and intrusive into user-device interactions, LLMs are eager for on-device execution to better preserve user privacy. In this work, we propose a new paradigm of mobile AI: LLM as a system service on mobile devices…

The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks…

The integration of wireless communications and Large Language Models (LLMs) is poised to unlock ubiquitous intelligent services, yet deploying them in wireless edge-device collaborative environments presents a critical trade-off between…

Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…

Large Language Models (LLMs) are increasingly deployed in multi-turn dialogue settings where preserving conversational context across turns is essential. A standard serving practice concatenates the full dialogue history at every turn,…

Applications are moving away from monolithic designs to microservice and serverless architectures, where fleets of lightweight and independently deployable components run on public clouds. Autoscaling serves as the primary control mechanism…

Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual adaptation. However, existing multi-agent memory designs…

This paper introduces a novel Large Language Models (LLMs)-assisted agent that automatically converts natural-language descriptions of power system optimization scenarios into compact, solver-ready formulations and generates corresponding…

Large Language Models (LLMs) pre-trained on internet-scale datasets have shown impressive capabilities in code understanding, synthesis, and general purpose question-and-answering. Key to their performance is the substantial prior knowledge…

Emergent communication enables partially observant Autonomous Mobile Robots (AMRs) to coordinate effectively in decentralized multi-agent reinforcement learning (MARL) settings. However, existing approaches often struggle with unstable…