| |
|
| Training Agents IRL
|
| With Ben Burtenshaw (Community Education in AI, HF), Govind Kamtamneni (Principal Research Engineer, Microsoft), Victor Barres (Researcher, Sierra), Zach Wentz (Member of Technical Staff, RL, Reflection), Tao Lin (Member of Technical Staff, RadixArk), Xiangyi Li (Founder, Benchflow). |
|
Oct 22 (Thu) @ 06:00 PM
FREE
| | GitHub, 88 Colin P Kelly Jr St, SF
|
|
|
|
|
| |
| Register |
|
|
| |
An open-source AI community event on reinforcement learning for agentic systems, hosted by GitHub & Hugging Face.
Join the open-source community at GitHub in San Francisco for an evening with researchers & builders exploring how AI agents are trained & evaluated.
We will look beyond single-turn RL to multi-step, environment-driven training: reward design, rollouts, benchmarks, & the practical gap between training gains & real-world agent behavior.
What to expect Short, 10-minute talks with Q&A, followed by a closing panel on what works in RL for agents, where the bottlenecks are, & what the open-source ecosystem needs next.
Speakers:
- Ben Burtenshaw (HF)
- Govind Kamtamneni (Microsoft)
- Victor Barres (Mercor)
- Zach Wentz (Reflection)
- Tao Lin (RadixArk)
- Xiangyi Li (Benchflow)
Who should attend
ML practitioners, agent builders, & RL researchers.
Thursday, October 22, 2026 6-9pm Pacific GitHub, San Francisco
This is part of Open Source AI Week.
|
|
|
|
|
|
|
|
