New York Working Group

Modeled on the Boston Working Group, the New York group brings together researchers in universities, labs and companies who evaluate agentic systems. The program is set by the organizers together with the members, and sessions are announced on the EvalScience calendar.

Each session, 6–9 PM

1. 6:00 PMArrival and food
2. 6:30Introductions and brief updates on current work
3. 6:50Presentations and discussions on early-stage and ongoing projects
4. 7:50Open discussion and networking: research problems, gaps in methods and infrastructure
5. 8:50Wrapping up and the next session
6. 9:00Close

The group meets monthly. Attendance is by approval and open to researchers with prior experience in agent evaluation.