Agentic AI for Science

On-site Workshop

  • Start: Oct 7, 2026
  • End: Oct 8, 2026
  • Location: Garching Campus Building D2
  • Room: Lecture Hall
  • Host: MPCDF
  • Contact: ai-training@mpcdf.mpg.de
A 2-day on-site workshop exploring how AI agents are reshaping scientific workflows, combining hands-on training and experiences from MPG institutes with perspectives from leading industry partners (Microsoft, AWS, AMD, NVIDIA).

AI agents are reshaping the way scientific research is conducted. Unlike traditional AI tools, agents can plan, reason across multiple sources, and carry complex tasks through many steps autonomously, from literature review and data analysis to code development and simulation workflows. This workshop brings together researchers, research software engineers, and industry partners to explore the current state and future potential of agentic AI in science.

The event is structured over two days and will be held in person at MPCDF, Garching bei München. Day 1 combines hands-on tutorials with real-world experiences from Max Planck researchers. Participants will get a practical introduction to AI agents followed by talks from MPG groups actively using agents in their research workflows. Day 2 broadens the perspective with contributions from leading industry partners, showcasing their latest solutions and discussing how agentic AI is being adopted across the research landscape.

The workshop is open to researchers across the Max Planck Society and aims to build a shared understanding of where agentic AI can genuinely add value, what the current limitations are, and how the community can approach adoption responsibly.

Day1

Foundations and AI-assisted scientific discovery at MPG

  • Morning: Foundations hands-on (MPCDF)

  • Afternoon: Experiences at MPG

Day2

Broader discussion around AI-assisted scientific discovery with industry partners.

  • Morning: Microsoft

  • Afternoon: AWS, AMD, NVIDIA


Registration via the event page: https://plan.events.mpg.de/e/ai-agents-for-science

Go to Editor View