5 papers
A Self-Defining Operator for Distributed Applications
Shihang Li, Thomas Anderson, Ratul Mahajan +2
To operate distributed applications with high availability, operators must rapidly diagnose and mitigate any incident. LLM-based agents can help, but unlike experienced human opera…
Agentic Societies Need a Social Harness
Tapan Chugh, Vidushi Singh, Krish Jain +2
An agentic society is a collection of AI agents that coordinate autonomously across trust boundaries on behalf of different principals. We show experimentally that in such societie…
CacheWise: Understanding Workloads and Optimizing KVCache Management for Efficiently Serving LLM Coding Agents
Shubham Tiwari, Tapan Chugh, Nash Rickert +3
Coding agents are a fast-growing LLM application, executing as long-running closed-loop sessions in which LLM generations alternate with external tool calls. Yet, unlike chat workl…
RNG: Flat Datacenter Networks at Scale
Giacomo Bernardi, Ratul Mahajan, C. Seshadhri +8
We design and deploy in production the first flat datacenter networks. Our design, called RNG, is based on quasi-random graphs. While the cost and fault-tolerance benefits of such…
Relational Network Verification
Xieyang Xu, Yifei Yuan, Zachary Kincaid +4
Relational network verification is a new approach to validating network changes. In contrast to traditional network verification, which analyzes specifications for a single network…