Amrutha Ramesh

Visiting Researcher

AI Frontier Research

Amrutha Varshini Ramesh is a Ph.D. candidate in Computer Science at the University of British Columbia, advised by Professor Mark Schmidt. Her research lies at the intersection of optimization and machine learning, with a particular focus on agentic AI and deep research systems. She is especially interested in building systems that can reason, adapt, and optimize themselves over extended sequences of tasks. Amrutha is currently a visiting researcher at ServiceNow, where she is developing AgentAda, a framework for tool-adaptive agents, and BigInsightBench, a benchmark designed to evaluate the deep research capabilities of autonomous agents across complex analytical workflows.

Interests

Machine Learning

Publications

AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery. Amirhossein Abaskohi, Amrutha Ramesh, Shailesh Nanisetty, Chirag Goel, David Vazquez, Christopher Pal, Spandana Gella, Giuseppe Carenini, Issam H. Laradji. At Workshop at the Annual Meeting of the Association for Computational Linguistics (ACL), 2025.

PDF Cite

BlockLLM: Memory-Efficient Adaptation of LLMs by Selecting and Optimizing the Right Coordinate Blocks. Issam H. Laradji, Amrutha Ramesh, Mark Schmidt. At Workshop at the Neural Information Processing Systems (NeurIPS), 2024.

PDF Cite