Join Our Paper Club with UBC on Automated Design of Agentic Systems
Event Ended
This event has already taken place.
The Paper Club is back! Our theme for Spring is AGENTS. Join us on March 27th at 12pm EST to meet with AI researcher Shengran Hu for a deep dive into Automated Design of Agentic Systems.
☝️ Register Above for this Live Virtual Meeting with the Researcher! ☝️

| Info | Details |
|---|---|
| Event | Paper Club with Shengran Hu on “Automated Design of Agentic Systems” |
| Date & Time | March 27, 2025, 12:00 PM EST - 1 PM EST |
| Presenter | Shengran Hu, AI Researcher with Sakana AI research lab in Tokyo, Japan. |
| Research Paper | Automated Design of Agentic Systems |
| Audio Version |
By Paper2Audio |
| Research Focus | Automatically create powerful agentic system designs |
Can AI agents design better AI agents?
Meet Shengran Hu is an AI Researcher with Sakana AI research lab in Tokyo, Japan, and a PhD student at the University of British Columbia, advised by Dr. Jeff Clune. His Automated Design of Agentic Systems paper presents a step toward full automation in agentic systems development from the bottom up in a self-referential manner.
Read the ADAS Paper: 📄 Automated Design of Agentic Systems
Key Insights for AI/ML Builders:
- Automated Design of Agentic Systems (ADAS): Learn about ADAS, which aims to automatically create powerful agentic system designs, including inventing novel building blocks and/or combining them in new ways.
- Meta Agent Search: New methodology to iteratively program new agents based on an ever-growing archive of previous designs and discoveries.
- Robustness and Generality: Understand how agents invented by Meta Agent Search maintain superior performance even when transferred across domains and models, demonstrating their robustness and generality. Meta-meta-meta agents are coming, hopefully to benefit humanity.
What is Paper Club?
Paper Club is a virtual event series brought to you by the Human Feedback Foundation in collaboration with AI Tinkerers, featuring authors of cutting-edge AI and machine learning papers. These online meetups allow attendees to hear about groundbreaking research directly from the authors, participate in live Q&A sessions, and engage in discussions. Open to all, Paper Club offers a regular opportunity to learn and interact with leaders in the rapidly evolving field of artificial intelligence.
Paper Club Organizers
This Paper Club is produced by the Human Feedback Foundation, a Linux Foundation AI & Data nonprofit advancing a human-centric future for AI, in collaboration with Mozilla AI and AI Tinkerers Global.
