8 papers
ASAP: Reimagining the Data Lifecycle using Application Semantic-Aware Processing
Milind Srivastava, Zeying Zhu, Yajie Zhou +5
Across many domains (e.g., observability, networking, security), data processing pipelines face what we refer to as the CSP problem: achieving low Cost at large Scale, while mainta…
TabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data
Jialin Zhang, Fenghao Dong, Yajie Zhou +2
Synthetic tabular data support use cases like data sharing, model development under access restrictions, and rapid prototyping of analytical workflows. Modern generative models are…
AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems
Yajie Zhou, Ao Li, Ashwin Silla +2
The computer systems community has recently seen growing interest in AI-driven system evolution, where AI agents iteratively rewrite systems. Frameworks such as AdaEvolve and Engra…
Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuel
Aadyaa Maddi, Prakhar Naval, Deepti Mande +3
Across many domains (e.g., IoT, observability, telecommunications, cybersecurity), there is an emerging adoption of conversational data analysis agents that enable users to "talk t…
AHA: Scalable Alternative History Analysis for Operational Timeseries Applications
Harshavardhan Kamarthi, Harshil Shah, Henry Milner +4
Many operational systems collect high-dimensional timeseries data about users/systems on key performance metrics. For instance, ISPs, content distribution networks, and video deliv…
Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks
Brian Singer, Keane Lucas, Lakshmi Adiga +3
Security operators use red teams to simulate real attackers and proactively find defense gaps. In realistic enterprise settings, this involves executing multi-host network attacks…