Related papers: Cortex: Workflow-Aware Resource Pooling and Schedu…
Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results. To improve robustness and solution quality, recent approaches deploy multiple agent teams running…
As autonomous coding agents become deeply embedded in software development workflows, their high operational velocity introduces a critical oversight challenge: the accumulating divergence between agentic actions and architectural intent.…
We propose an implementation of an interior-point-based nonlinear predictive controller on a heterogeneous processor. The workload can be split between a general-purpose CPU and a field-programmable gate array to trade off the contradicting…
Large Language Models (LLMs) are increasingly being deployed as intelligent agents. Their multi-stage workflows, which alternate between local computation and calls to external network services like Web APIs, introduce a mismatch in their…
Recent advances in agentic AI have enabled increasingly autonomous workflows, but existing systems still face substantial challenges in achieving reliable deployment in real-world scientific research. In this work, we present a safe,…
Current multi-agent Large Language Model (LLM) frameworks suffer from linear memory scaling, rendering "System 2" parallel reasoning impractical on consumer hardware. We present Warp Cortex, an asynchronous architecture that theoretically…
While prior researches focus on CPU-based microservices, they are not applicable for GPU-based microservices due to the different contention patterns. It is challenging to optimize the resource utilization while guaranteeing the QoS for GPU…
Agentic artificial intelligence (AI) is an AI paradigm that can perceive the environment, reason over observations, and execute actions to achieve specific goals. Task-oriented communication supports agentic AI by transmitting only the…
Cloud computing is a model for enabling on-demand network access to a shared pool of computing resources, that can be dynamically allocated and released with minimal effort. However, this task can be complex in highly dynamic environments…
Extracting actionable insights from complex value stream map simulations can be challenging, time-consuming, and error-prone. Recent advances in large language models offer new avenues to support users with this task. While existing…
Large language model (LLM) based agentic workflows have become a popular paradigm for coordinating multiple specialized agents to solve complex tasks. To improve serving efficiency, existing LLM systems employ prefix caching to reuse…
Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and more effective scaffolding. In contrast, much less is understood about scaling out: whether…
Serverless computing has emerged as a promising computing paradigm for edge computing. However, adopting the event driven model in highly dynamic, heterogeneous, and distributed edge systems poses significant challenges in request placement…
The rise of multi-agent systems powered by large language models (LLMs) and specialized reasoning agents exposes fundamental limitations in today's data management architectures. Traditional databases and data fabrics were designed for…
Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators. Agentic workloads induce a temporal shift from single-turn inference to multi-turn LLM-tool loops,…
The Agentic Service Ecosystem consists of heterogeneous autonomous agents (e.g., intelligent machines, humans, and human-machine hybrid systems) that interact through resource exchange and service co-creation. These agents, with distinct…
Agentic systems, in which diverse agents cooperate to tackle challenging problems, are exploding in popularity in the AI community. However, existing agentic frameworks take a relatively narrow view of agents, apply a centralized model, and…
Recent advancements in AI and edge computing have accelerated the development of machine-centric applications (MCAs), such as smart surveillance systems. In these applications, video cameras and sensors offload inference tasks like license…
Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution. However, the effective adjustment of agentic workflows during execution has not been well studied. An…
Multi-stage serverless applications, i.e., workflows with many computation and I/O stages, are becoming increasingly representative of FaaS platforms. Despite their advantages in terms of fine-grained scalability and modular development,…