I am a research PhD student in the Social Cognitive Systems Group at Bielefeld University since December 2022.
My research focuses on theory of mind and mentalizing for multi-agent cooperation. I am interested in integrating these capabilities into a socio-cognitive interaction architecture, including decision-making, knowledge representation and behavior execution. I supervise the tutorials of the lectures “Foundations of Artificial Cognition” and “Language and Interaction”. I have also run seminars on Human-Aware AI and Socially Assistive Robots. During my master studies, I worked as a research assistant in the VIVA project. There, I worked on the development of interactive and explainable social robots.
Checkout CoCu, an interactive cooperative environment for humans and agents. It is open-source and super extensible.
Fast collaboration requires making quick, good-enough decisions about what to do and who does it, without waiting for slow deliberation. This thesis …
In a time-pressured kitchen, a collaborative agent that talks too much slows both itself and its human partner down. This thesis explores how such an …
A behavior tree (BT) is a compact and interpretable way to represent tasks and their structure. When a language model has to reason about those tasks, …
Our comprehensive paper on how to make human-agent collaboration in dynamically changing environments sufficiently flexible and adaptive (i.e., fluid) …
Florian went to the Int. Conference on Hybrid Human-AI Interaction (HHAI 2025), held in Pisa (Italy) and presented work on collaborative AI agents …
Florian’s paper “Towards Action-Driven Mentalizing in Realtime Human-Agent Collaboration” has been accepted at the 1st Workshop on …