Related papers: Agent.xpu: Efficient Scheduling of Agentic LLM Wor…

Modern information systems require autonomous agents capable of navigating complex workflows, yet current methodologies often struggle with the transition from structured metadata parsing to general environmental perception. While the…

Efficiently serving Large Language Models (LLMs) requires selecting an optimal parallel execution plan, balancing computation, memory, and communication overhead. However, determining the best strategy is challenging due to varying…

Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval, tool use, code execution, memory updates, and verification.…

Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reasoning and tool-use steps, leaving control flow and intermediate state implicit and making…

We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP). AgentOptics interprets natural language tasks and executes protocol-compliant actions on…

Due to decelerating gains in single-core CPU performance, computationally expensive simulations are increasingly executed on highly parallel hardware platforms. Agent-based simulations, where simulated entities act with a certain degree of…

Chemical process optimization maximizes production efficiency and economic performance, but optimization algorithms, including gradient-based solvers, numerical methods, and parameter grid searches, become impractical when operating…

Modern agentic frameworks (e.g., CrewAI and AutoGen) have evolved into complex, autonomous multi-agent systems, introducing unique reliability challenges beyond earlier pipeline-based LLM libraries. However, existing empirical studies focus…

Large language models (LLMs) have enabled a new class of agentic AI systems that reason, plan, and act by invoking external tools. However, most existing agentic architectures remain centralized and monolithic, limiting scalability,…

Scientific workflow systems automate execution -- scheduling, fault tolerance, resource management -- but not the semantic translation that precedes it. Scientists still manually convert research questions into workflow specifications, a…

LLM-based agents have emerged as transformative tools capable of executing complex tasks through iterative planning and action, achieving significant advancements in understanding and addressing user needs. Yet, their effectiveness remains…

Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling input queries across different LLM instances in a cluster.…

LLM deployment on resource-constrained edge devices faces severe latency constraints, particularly in real-time applications where delayed responses can compromise safety or usability. Among many approaches to mitigate the inefficiencies of…

Artificial intelligence (AI) is increasingly deployed in real-time and energy-constrained environments, driving demand for hardware platforms that can deliver high performance and power efficiency. While central processing units (CPUs) and…

Agentic workflows have emerged as a powerful paradigm for solving complex, multi-stage tasks, but serving them at scale is computationally expensive given the many LLM inferences that each request must pass through. Configuration selection,…

Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code…

Agents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in production environments can be challenging due to asynchrony and failures. In this paper, we…

LLM agents increasingly adopt skills as a reusable unit of composition. While skills are shared across diverse agent platforms, current systems treat them as raw context, causing the same skill to behave inconsistently for different agents.…

Autonomous, goal-driven agents powered by LLMs have recently emerged as promising tools for solving challenging problems without the need for task-specific finetuned models that can be expensive to procure. Currently, the design and…

Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution…