Related papers: FATE: Future-State-Aware Scheduling for Heterogene…

Prognostics and health management (PHM) technology plays a critical role in industrial production and equipment maintenance by identifying and predicting possible equipment failures and damages, thereby allowing necessary maintenance…

This work studies fixed priority (FP) scheduling of real-time jobs with end-to-end deadlines in a distributed system. Specifically, given a multi-stage pipeline with multiple heterogeneous resources of the same type at each stage, the…

Multi-agent LLM systems are increasingly used to solve complex tasks through decomposition, debate, specialization, and ensemble reasoning. However, these systems are usually evaluated in terms of robustness: whether performance is…

Federated edge learning (FEEL) enables collaborative model training across distributed clients over wireless networks without exposing raw data. While most existing studies assume static datasets, in real-world scenarios clients may…

Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representative samples from past tasks. Existing studies focus on designing sample-importance…

We propose Heterogeneous Swarms, an algorithm to design multi-LLM systems by jointly optimizing model roles and weights. We represent multi-LLM systems as directed acyclic graphs (DAGs) of LLMs with topological message passing for…

Accurately predicting traffic accidents in real-time is a critical challenge in autonomous driving, particularly in resource-constrained environments. Existing solutions often suffer from high computational overhead or fail to adequately…

Enterprises increasingly need natural language (NL) question answering over hybrid data lakes that combine structured tables and unstructured documents. Current deployed solutions, including RAG-based systems, typically rely on brute-force…

Federated learning (FL) enables collaborative model training across distributed devices while preserving data privacy, but deployment on resource-constrained edge nodes remains challenging due to limited memory, energy, and communication…

Modern logistics networks generate rich operational data streams at every warehouse node and transportation lane -- from order timestamps and routing records to shipping manifests -- yet predicting delivery delays remains predominantly…

Large language model (LLM) agents execute tasks through multi-step workflows that combine planning, memory, and tool use. While this design enables autonomy, it also expands the attack surface for backdoor threats. Backdoor triggers…

Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent characteristics: prompt segmentation (e.g., system instructions, retrieved passages, tool…

Large Language Model (LLM) inference has emerged as a fundamental paradigm, however, variations in output length cause severe workload imbalance in the decode phase, particularly for long-output reasoning tasks. Existing systems, such as PD…

Large Language Models (LLMs) have proven immensely beneficial in education by capturing vast amounts of literature-based information, allowing them to generate context without relying on external sources. In this paper, we propose a…

The exploration and application of Large Language Models (LLMs) is thriving. To reduce deployment costs, continuous batching has become an essential feature in current service frameworks. The effectiveness of continuous batching relies on…

As modern HPC computing platforms become increasingly heterogeneous, it is challenging for programmers to fully leverage the computation power of massive parallelism offered by such heterogeneity. Consequently, task-based runtime systems…

The adoption of large language models (LLMs) for structured information extraction from financial documents has accelerated rapidly, yet production deployments face fundamental architectural decisions with limited empirical guidance. We…

This paper addresses emerging system-level challenges in heterogeneous retrieval-augmented generation (RAG) serving, where complex multi-stage workflows and diverse request patterns complicate efficient execution. We present HedraRAG, a…

LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to improve throughput, they still rely on unified scheduling…

Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…