Agent Evaluation Science Bay Area Gathering

​Agent Evaluation Science (AES) is bringing together researchers from academia and industry who are interested in building more rigorous approaches to AI agent evaluation and developing a stronger scientific foundation for the field.

​This will be a small, curated group with a short guided introduction and discussion, followed by networking. Participants will briefly introduce their work and share perspectives on the discussion questions included in the participation questionnaire.

​You do not need to answer every question, but please come prepared to speak for 1–2 minutes about those most relevant to your work.

​Taking place shortly after COLM and just before Stanford Reunion Week, this gathering is an opportunity to connect with researchers and alumni from across the country who will be in the Bay Area. We especially welcome researchers working on measurement, reliability and validity, evaluation infrastructure, AI safety, and deployed agent systems.