ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2606.00866· 20 results

cs.OScs.AIcs.DCEmpiricalRecentAug 15, 2026

From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

Chaokun Chang, Yukun Zhou, Kaihua Fu, Dakai An +9 more

This paper introduces AgentSysBench, a benchmark suite and measurement toolkit for agentic applications, and identifies six properties that distinguish agentic workloads from conventional LLM serving.

View →
cs.DCcs.OSEmpiricalRecentJun 15, 2026

CacheWise: Understanding Workloads and Optimizing KVCache Management for Efficiently Serving LLM Coding Agents

Shubham Tiwari, Tapan Chugh, Nash Rickert, Simon Peter +2 more

This paper presents a new KVCache management layer called CacheWise that improves performance for coding agent workloads.

View →
cs.AREmpiricalRecentJul 27, 2026

PIMID: A Full-System Simulator with Intricacy and Diversity for Processing-in-Memory

Yuan He, Masaaki Kondo, Galen M. Shipman, Jered B. Dominguez-Trujillo +2 more

PIMID is an execution- and trace-driven full-system simulator for Processing-in-Memory systems, supporting multiple memory technologies, execution models, and placement of processing elements.

View →
cs.OScs.ARcs.NIEmpiricalRecentJul 17, 2026

Rethinking Polling Efficiency in Service Core Network Stacks

Matheus Stolet, Simon Peter, Antoine Kaufmann

This paper argues that idle cores on contemporary multicore processors can return compute capacity and proposes a budget-centric view of service core systems.

View →
cs.DCEmpiricalRecentJul 24, 2026

Agentic CPU-GPU Scheduling for Heterogeneous AI Workloads

Tianxi Lu, Sherief Reda

This paper identifies suboptimalities in default GPU-first scheduling for AI tool workloads and proposes an agentic scheduler that adaptively assigns tools to GPU or CPU based on runtime factors.

View →
cs.DCEmpiricalRecentOct 27, 2026

TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving

Shuhuai Li, Shengdong Ye, Dongdong Ge, Yinyu Ye +1 more

This paper presents TAO, a tool-aware joint scheduling framework for LLM-based agentic serving that reduces latency, mean time to first token, and increases decode throughput.

View →
cs.DCEmpiricalRecentJul 28, 2026

CW-Ghost: Search-Free Granularity Selection for Helper-Thread Prefetching via Capacity Windows

Ya Zhang, Tong Lei, Yao Chen, Yonggang Che +3 more

This paper introduces CW-Ghost, a method for estimating cache line fill volume and determining helper-thread prefetching granularity based on cache capacity constraints.

View →
cs.LGcs.AIcs.CLEmpiricalRecentNov 12, 2026

Metal Sandbox: Isolated Execution and Command Scheduling for GPU Coding Agents on Apple Silicon

Haozhe Wang, Lina Chen, Fanqi Wan, Qi Han +4 more

This paper presents Metal Sandbox, a system for efficient on-device inference on macOS that combines restricted file access, native command execution, and command-level scheduling.

View →
cs.DCcs.AIcs.LGEmpiricalRecentJun 23, 2026

CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation

Zhuoren Ye, Tianyu Wo, Dinghao Xue, Mingming Zhang +3 more

This paper proposes CrossPool, a serving engine for cold Machine Learning Models (LLMs) that separates weights and KV-cache into two GPU memory pools to improve GPU memory utilization and long-context…

View →
cs.DCEmpiricalRecentJun 20, 2026

StickyInvoc: Rethinking Task Models for High-throughput Workflows in the LLM Era

Thanh Son Phung, Douglas Thain

This paper proposes StickyInvoc, a task model that reduces overhead in high-throughput workflows by decoupling state creation and destruction for LLM inference tasks.

View →
cs.OSEmpiricalRecentOct 18, 2026

AgentLens: Framework-Aware Characterization and Resource Control for Heterogeneous LLM Agents

Wentao Hong

Combines cross-framework workload characterization with framework-aware resource controller for co-located agents

View →
cs.SEcs.AIEmpiricalRecentJun 10, 2026

Characterizing Software Aging in GPU-Based LLM Serving Systems

Domenico Cotroneo, Bojan Cukic

This paper studies software aging in GPU-based LLM serving systems using a 216-hour campaign.

View →
cs.DCEmpiricalRecentAug 13, 2026

Balancing Workload Performance and Slurm Stress: Four Nextflow Deployment Strategies

Nil Tianchen Mu, William Dizon, Glen Otero, Torey Battelle

This paper presents a measurement protocol and benchmarking harness for evaluating the performance of different multi-node strategies for submitting tasks on shared Slurm clusters, focusing on their i…

View →
cs.ARcs.PFRecentMay 30, 2026

Regular-Dead on Arrival: Characterizing and Protecting Against Dead-Entry TLB Misses in GPU Microarchitectures

Shafayat Mowla Anik, Yongchan Jung, Jeeho Ryoo, Byeong Kil Lee

The paper characterizes 'dead-entry' TLB misses in GPUs, which occur when recently evicted translations are immediately re-walked, and proposes DEPOT, a Bloom filter mechanism that significantly reduc…

View →
cs.AIcs.AREmpiricalRecentAug 10, 2026

ArchAgent v2: A Case Study with the Data Prefetching Championship

Abraham Gonzalez, Raghav Gupta, Akanksha Jain, Hanna Alam +11 more

This paper presents ArchAgent v2, a framework that scales automated microarchitecture search to multi-level data prefetching using a cascaded evolutionary search and hardware-realizability feedback lo…

View →
cs.DCEmpiricalRecentJul 31, 2026

Rethinking AI Cloud Infrastructure for Agentic Serving Systems with the Aries Experimentation Framework

Leonid Kondrashov, Hongrui Liu, JooYoung Park, Boxi Zhou +13 more

Aries is a full-stack experimentation framework for autonomous agents that separates task semantics from execution configurations, reconstructs agent trajectories, and exposes stateful tool execution.

View →