Trustworthy Agentic Systems

Seminar Description

When AI systems move from pattern recognition to decision-making, they stop being just tools and start becoming agents. These agents can plan, act, and adapt, qualities that make them powerful but also raise questions about reliability, safety, and alignment with human goals.

This seminar investigates what it means to build trustworthy agentic systems. Instead of focusing on scale or efficiency, we’ll center on issues like:

How do we evaluate whether an AI system deserves trust?
What design principles can reduce the risks of unintended behavior?
How can humans and AI collaborate without losing oversight or control?

By the end of the seminar, you’ll have a deeper grasp of the challenges that lie ahead for autonomous AI and the frameworks researchers are developing to meet them.

 

Organization

The seminar is structured into xyz parts....

• Part 1:
• Part 2

Everyone must attend .... The seminar will take place every Tuesday from 2.15 pm until 3.45pm (room TBA)

Presentation

Everyone will be assigned a topic for which you will .... We will have the following topics:

• Topic 1: Defining Trust in AI – What does it mean for an AI agent to be “trustworthy”?
  • ...
• Topic 2: Agency vs. Tool Use – How autonomous systems differ from traditional ML models
  • ...
• Topic 3: Uncertainty and Robustness – Designing agents that can handle incomplete or noisy information
• Topic 4: Interpretability and Transparency – Making the reasoning of agents understandable to humans
• Topic 5: Multi-Agent Safety – Coordination, competition, and failure modes in environments with many interacting agents
• Topic 6: 
• Topic 7: 
• Topic 8:
• Topic 9: 
• Topic 10: 
• Topic 11: 
• Topic 12: 
  • ...

 

Schedule

The seminar will take place in xxx

• Oct 21: Kick-off 
• Oct 28: Topic assignment
• Nov 4: ...