Francesco Fabiano

I’m Francesco, Ph.D. in Computer Science and currently AI researcher at the Erlangen AI Hub, University of Oxford.

Throughout my academic journey, I’ve had the privilege of collaborating with exceptional researchers worldwide on topics such as epistemic planning and hybrid AI architectures. More recently, my research has centered on understanding decision making, multi-agent planning and human-inspired AI systems.

I believe that being a researcher in AI today is especially important as we have a responsibility to ensure that our work leads to trustworthy and socially beneficial AI systems.

Outside academia, I enjoy trail running and reading about mythology.

I have taught a variety of courses at institutions in both Europe and the United States. My teaching experience spans topics such as Programming (C++, Scala, and Python), Algorithms and Data Structures, and Machine Learning. I am currently teaching Imperative Programming at Trinity, where I enjoy helping students build strong foundations in computational thinking.

I have supervised numerous students during their theses and master’s projects, many of which have led to publications and ongoing collaborations. I particularly enjoy mentoring students exploring the intersections of logic and Machine Learning.

If you are interested in a research-focused undergraduate thesis or a master’s project related to any of my research areas, please feel free to get in touch.

AI research seeks to build systems capable of reasoning, interacting, and adapting in ways that resemble (or surpass) human intelligence, and among its many challenges, two have particularly captured my interest.

The first is understanding how to formally model complete multi-agent interactions through epistemic logic. This involves enabling agents to reason about their own and others’ beliefs, knowledge, and intentions. My work in this area focuses on building logical frameworks that allow such interactions to be represented and solved effectively, bridging the gap between formal reasoning and practical AI applications.

The second is exploring how insights from human cognition can inspire the design of artificial reasoning systems. In particular, I investigate neuro-symbolic architectures that integrate System 1 and System 2–like mechanisms to address complex decision-making problems.

Together, these directions aim to contribute to the creation of trustworthy AI systems in which agents that can not only plan and collaborate effectively but also enrich their reasoning with logic and experience.

A complete list of my publications can be found on my DBLP and Google Scholar pages.

Francesco Fabiano et al. ‘Thinking Fast and Slow in Human and Machine Intelligence’. In: Commun. ACM 68.8 (July 2025), pp. 72–79. issn: 0001-0782. doi: 10.1145/3715709.

Vishal Pallagani et al. ‘On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS).’ In: Proceedings of ICAPS 2024, Banff, Alberta, Canada, June 1-6, 2024. 2024, pp. 432–444. doi: 10.1609/ICAPS.V34I1.31503.

A. Burigana, F. Fabiano, A. Dovier, and E. Pontelli ‘Modelling Multi-Agent Epistemic Planning in ASP.’ In: Theory Pract. Log. Program.20.5 (2020), pp. 593–608. doi: 10.1017/S1471068420000289.