Master Thesis - Evaluating Multi-Agentic AI Systems in Practical Applications

Are you a master’s student in Computer Science looking for an innovative company to collaborate with on your master’s thesis during the spring semester of 2026? Look no further. 

ASSA ABLOY is the global leader in access solutions and provides the latest technologies to give access to physical and virtual spaces for millions of people every day. Joining ASSA ABLOY means being part of a fast-moving and highly innovative company with diverse opportunities in more than 70 countries worldwide.

What can you expect as a master’s thesis intern at ASSA ABLOY? Cutting edge technology, a steep learning curve, dedicated supervisors from within the enterprise, a group of fellow master's thesis students to share the experience with – and much more.

We have an exciting range of subjects. Please remember to indicate in your application if you're interested in other subjects as well and mark them in your order of preference. Please also let us know your thoughts on how you would approach the subject. Please note that most of your work will be done at our HQ in Stockholm.

While we aim to support all proposed thesis subjects, we may need to change or cancel a project due to unexpected circumstances.

Master thesis nr 5 - Evaluating Multi-Agentic AI Systems in Practical Applications

Multi-agentic AI systems, where several large language model (LLM)-based agents collaborate or coordinate to solve complex tasks, are being increasingly developed and used in modern business solutions. However, systematic methods for evaluating such systems in real-world applications are limited. A recent survey in this field highlights key gaps, noting the need for scalable evaluation solutions that consider cost, safety, and robustness [1].

This project aims to approach the challenge of evaluating multi-agentic systems and address the gaps in the field through the evaluation of a multi-agentic system developed in-house at ASSA ABLOY. The goal of this project is to generate insights on how to evaluate and improve such systems in practical business settings.

Objective

· Contribute to a reproducible evaluation process for multi-agentic AI systems within an applied business environment.

· Explore and define evaluation dimensions and best practices suited to the chosen multi-agent application.

· Investigate and apply existing evaluation techniques to derive practically useful insights for system design and improvement.

Focus Areas

· How can evaluation insights be integrated into the development and improvement of the agent pipeline?

· What constitutes reliable and interpretable evaluations of multi-agentic AI systems in practice?

· How can existing evaluation techniques be used in or adapted to ASSA ABLOY applications?

Expected Outcome

· Contributions to an internal evaluation pipeline, enabling more systematic analysis of agentic AI behavior.

· Insights, knowledge, and recommendations on suitable evaluation techniques for the in-house multi-agentic system, derived through an academic research process.

This position is ideal for two MSc. thesis students with a background in AI and machine learning with experience with LLMs. If you are interested in further readings (e.g., the cited survey) or have any related questions, feel free to reach out to samuel.hoglund@assaabloy.com.

We Look Forward to Your Application!

Please include your CV, university transcripts, resumé and a short description of how you would approach this thesis topic.

We are the ASSA ABLOY Group
Our people have made us the global leader in access solutions. In return, we open doors for them wherever they go. With nearly 63,000 colleagues in more than 70 different countries, we help billions of people experience a more open world. Our innovations make all sorts of spaces – physical and virtual – safer, more secure, and easier to access. 

As an employer, we value results – not titles, or backgrounds. We empower our people to build their career around their aspirations and our ambitions – supporting them with regular feedback, training, and development opportunities. Our colleagues think broadly about where they can make the most impact, and we encourage them to grow their role locally, regionally, or even internationally.

As we welcome new people on board, it’s important to us to have diverse, inclusive teams, and we value different perspectives and experiences.