LADs
Six-agent framework for configuration, deployment, monitoring, and repair. First author, MLSys 2027 submission.
LADs: Leveraging LLMs for AI-Driven DevOps
Fall 2025 – Spring 2026 · First author
Advisors: Dr. Ali Anwar (University of Minnesota) and Dr. Ali R. Butt (Virginia Tech)
Co-developed a six-agent framework for configuration, deployment, monitoring, and automated repair.
- Achieved 68% deployment success across 180 Dask, Redis, and Ray tasks.
- Repaired 94% of runtime failures within three iterations.
- Adapted two existing systems as baselines and substantially redesigned the evaluation and technical presentation to better establish LADs’ gains over prior approaches.
Impact: Submission at MLSys 2027. Download the paper (PDF)