Prof. Baochun Li

University of Toronto, Canada

Abstract

As AI agents become part of everyday computing, the need for flexible, easy-to-use, and high-performance research testbeds for network experimentation has become more pressing than ever. In this talk, I will present two systems that we have been working on over the recent years: Nextmini, our new network experimental substrate and Flies, a production-quality runtime for safe self-modifying distributed multi-agent workflows. Nextmini reflects our latest design principles and thoughts on a modern open-source network experimental testbed. Powered by Rust, it balances flexible user-space experimentation with high-performance forwarding, supports unmodified application workloads, and scales from a single machine to multiple geographically distributed datacenters. (Flies), on the other hand, is our recent take on a new production-quality safe runtime for distributed multi-agent workflows, ideally suited for harness engineering. These workflows are self-modifying in nature, and tasks that are generated at runtime must be assigned to sandboxes to run safely. They run over any network substrate, including Nextmini. Together, these systems point toward a new experimental stack for distributed multi-agent workflows in the age of AI agents.

Biography

Baochun Li received his B.Engr. degree from the Department of Computer Science and Technology, Tsinghua University, China, in 1995 and his M.S. and Ph.D. degrees from the Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, in 1997 and 2000. Since 2000, he has been with the Department of Electrical and Computer Engineering at the University of Toronto, where he is currently a Professor. He holds the Bell Canada Endowed Chair in Computer Engineering since August 2005. His current research interests include cloud computing, security and privacy, distributed machine learning, federated learning, and networking.
Dr. Li has co-authored more than 500 research papers, with a total of over 29000 citations, an H-index of 91 and an i10-index of 370, according to Google Scholar Citations. He was the recipient of the IEEE Communications Society Leonard G. Abraham Award in the Field of Communications Systems in 2000, the Multimedia Communications Best Paper Award from the IEEE Communications Society in 2009, the University of Toronto McLean Award in 2009, the Best Paper Award from IEEE INFOCOM in 2023, and the IEEE INFOCOM Achievement Award in 2024. He is a Fellow of the Canadian Academy of Engineering, a Fellow of the Engineering Institute of Canada, and a Fellow of IEEE.