4 citations · 12 across the 17 of their papers we have counts for
20 papers
Do Coding Agents Understand Why Systems Crash---and Why They Don't?
Chenxi Huang, Haonan Wang, Jinghe Zhang +7
Coding agents are increasingly capable of fixing real-world bugs, yet they still struggle with large systems codebases such as the Linux kernel. To understand why, we test how agen…
Probe-and-Resume: When and How to Evaluate Agent Execution
Jiakai Xu, Tiancheng Ge, Tujie Guan +4
Test-time search can improve agent performance by exploring alternative actions and using a critic to select promising branches. We study this approach in terminal-based computer-u…
StateFork: Branchable Infrastructure for Agent Exploration
Jiakai Xu, Tianle Zhou, Georgios Liargkovas +5
AI agents improve task success by exploring multiple trajectories, but for computer-use agents each trajectory modifies external environment state. Branching from an intermediate p…
TuxBot: Semantic-Aware Online OS Tuning with Large Language Models
Georgios Liargkovas, Mihir Nitin Joshi, Hubertus Franke +1
Online OS tuning can improve long-running services, but existing controllers are poorly matched to live hosts. They treat scheduler, power, memory, and I/O controls as black-box va…
BranchBench: Aligning Database Branching with Agentic Demands
Elaine Ang, Sam Weldon, In Keun Kim +3
Branchable databases are evolving from developer tools to infrastructure for agentic workloads characterized by speculative mutations and non-linear state exploration. Traditional…
AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent
Wenyue Hua, Sripad Karne, Qian Xie +4
AI agents are increasingly deployed in real-world applications, including systems such as Manus, OpenClaw, and coding agents. Existing research has primarily focused on server-side…
VineLM: Trie-Based Fine-Grained Control for Agentic Workflows
Nikos Pagonas, Matthew Lou, Tianyi Peng +2
Agentic workflows interleave configurable LLM stages with tool stages and often include retries or refinement loops. Existing workflow managers profile full workflow configurations…
Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All
Chenxi Huang, Alex Mathai, Feiyang Yu +7
Repairing system crashes discovered by kernel fuzzers like Syzkaller is a critical yet underexplored challenge in software engineering. While recent works have introduced Large Lan…
Harvest: Opportunistic Peer-to-Peer GPU Caching for LLM Inference
Nikhil Gopal, Kostis Kaffes
Large Language Model (LLM) inference is increasingly constrained by GPU memory capacity rather than compute throughput, driven by growing model sizes and the linear growth of the k…
Cortex: Workflow-Aware Resource Pooling and Scheduling for Agentic Serving
Nikos Pagonas, Yeounoh Chung, Kostis Kaffes +1
We introduce Cortex, a prototype workflow-aware serving platform designed for agentic workloads. The core principle of Cortex is stage isolation: it provisions dedicated resource p…
Toward Systems Foundations for Agentic Exploration
Jiakai Xu, Tianle Zhou, Eugene Wu +1
Agentic exploration, letting LLM-powered agents branch, backtrack, and search across many execution paths, demands systems support well beyond today's pass-at-k resets. Our benchma…
Speculative Actions: A Lossless Framework for Faster Agentic Systems
Naimeng Ye, Arnav Ahuja, Georgios Liargkovas +3
AI agents are increasingly deployed in complex, interactive environments, yet their runtime remains a major bottleneck for training, evaluation, and real-world use. Typical agent b…
Fast Userspace Networking for the Rest of Us
Alireza Sanaee, Vahab Jabrayilov, Ilias Marinos +5
After a decade of research in userspace network stacks, why do new solutions remain inaccessible to most developers? We argue that this is because they ignored (1) the hardware con…
Wave: Offloading Resource Management to SmartNIC Cores
Jack Tigar Humphries, Neel Natu, Kostis Kaffes +5
SmartNICs are increasingly deployed in datacenters to offload tasks from server CPUs, improving the efficiency and flexibility of datacenter security, networking and storage. Optim…
Shabari: Delayed Decision-Making for Faster and Efficient Serverless Functions
Prasoon Sinha, Kostis Kaffes, Neeraja J. Yadwadkar
Serverless computing relieves developers from the burden of resource management, thus providing ease-of-use to the users and the opportunity to optimize resource utilization for th…
BPF-oF: Storage Function Pushdown Over the Network
Ioannis Zarkadas, Tal Zussman, Jeremy Carin +8
Storage disaggregation, wherein storage is accessed over the network, is popular because it allows applications to independently scale storage capacity and bandwidth based on dynam…
Towards Fast, Adaptive, and Hardware-Assisted User-Space Scheduling
Lisa, Li, Nikita Lazarev +7
Modern datacenter applications are prone to high tail latencies since their requests typically follow highly-dispersive distributions. Delivering fast interrupts is essential to re…
Apiary: A DBMS-Integrated Transactional Function-as-a-Service Framework
Peter Kraft, Qian Li, Kostis Kaffes +16
Developers increasingly use function-as-a-service (FaaS) platforms for data-centric applications that perform low-latency and transactional operations on data, such as for microser…
Practical Scheduling for Real-World Serverless Computing
Kostis Kaffes, Neeraja J. Yadwadkar, Christos Kozyrakis
Serverless computing has seen rapid growth due to the ease-of-use and cost-efficiency it provides. However, function scheduling, a critical component of serverless systems, has bee…
RackSched: A Microsecond-Scale Scheduler for Rack-Scale Computers (Technical Report)
Hang Zhu, Kostis Kaffes, Zixu Chen +4
Low-latency online services have strict Service Level Objectives (SLOs) that require datacenter systems to support high throughput at microsecond-scale tail latency. Dataplane oper…