Eric Zhu

I am a Senior Researcher at Microsoft Research, focusing on AI agents. I have also worked on database research. My current project is AutoGen (github.com/microsoft/autogen), an open-source framework for building AI agents and multi-agent systems. AutoGen is a central hub that brings together agentic AI research and applications, like PyTorch for deep learning. I am a core maintainer of the project. Before joining Microsoft Research, I completed my PhD in Computer Science at the University of Toronto, under the guidance of Prof. Renée J. Miller. My thesis is in dataset search over massive Open Data archives. Specifically, I contributed algorithms for large-scale set similarity search (github.com/ekzhu/setsimilaritysearch) and data sketches (github.com/ekzhu/datasketch). These algorithms can find joinable or unionable tables from over 100K tables in milliseconds. Based on my research work, I built an Open Data search engine stack to make it easy for people to use Open Data in their applications.

Advancing AutoGen: Present and Future

In this keynote, we will explore the capabilities and advancements of Microsoft’s AutoGen framework, an innovative system for creating AI agents and automating complex workflows. We will dive into its current architecture, real-world applications, and how it streamlines AI development. Additionally, we’ll present our roadmap for the next version, highlighting exciting new features and enhancements designed to push the boundaries of autonomous systems even further. This talk is for anyone interested in the future of AI-driven automation and multi-agent frameworks.