Neuro-Symbolic Decision-Making for Autonomous Agents: a Dual Process Theory Approach

About the Project

These projects are open to students worldwide, but have no funding attached. Therefore, the successful applicant will be expected to fund tuition fees at the relevant level (home or international) and any applicable additional research costs. Please consider this before applying.

There is a growing body of research on Neuro-Symbolic Artificial Intelligence, reflecting efforts to integrate learning-based and logic-based reasoning. However, most existing work concentrates on inference, prediction, and recognition tasks, while the challenge of autonomous decision-making in embodied or agentic AI systems remains largely unexplored. In particular, there is limited progress on developing domain-independent reasoning architectures that are explainable, formally verifiable, and capable of adaptive behaviour in complex, real-world environments.

Dual process theory—a foundational concept in cognitive psychology—offers a compelling model for bridging this gap. It describes two complementary systems of human thought: System 1, responsible for intuitive and rapid responses, and System 2, responsible for reflective and deliberative reasoning [1]. While this framework has been discussed in Neuro-Symbolic AI [2,3,4], its potential for autonomous decision-making has not been fully realised.

In this PhD project, you will explore how System 1 can be represented by sub-symbolic AI (learning components capturing fast, experience-driven decisions) and System 2 by symbolic AI (logical and deliberative reasoning). The key objective is to identify when and how an autonomous agent should engage learning or deliberative reasoning, and to design mechanisms that combine both effectively to enhance performance, explainability, and safety.

The research will be applied to real-world case studies in collaboration with industry and academic partners, focusing on challenging domains such as self-driving vehicles and robotics. The ultimate goal is to develop a neuro-symbolic framework for reliable and explainable autonomous reasoning.

Informal enquiries can be directed to Dr Rafael Cardoso (rafael.cardoso@abdn.ac.uk) if the topic within this project is of interest to you, he is happy to discuss further with interested candidates.

Decisions will be based on academic merit. The successful applicant should have, or expect to obtain, a UK Honours Degree at 2.1 (or equivalent) in computer science, mathematics or a related discipline. Candidates should also have demonstrably strong programming skills and a keen interest in the area and enjoy working collaboratively.

We will give priority to candidates with experience with at least one of the following topics:

• Symbolic AI (rule-based systems, Belief-Desire-Intention agents, knowledge graphs, etc.)
• Deep Learning
• Dual Process Theory

Applications from candidates belonging to demographics typically underrepresented in AI are particularly encouraged to apply.

Finally, applications from candidates with backgrounds that are not an exact match to the above, but provide a solid foundation to support PhD study are encouraged to apply, making clear how this background will support their work.

This PhD can be run in distance mode if necessary.

We encourage applications from all backgrounds and communities, and are committed to having a diverse, inclusive team.

Application Procedure:

Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php.

You should apply for Degree of Doctor of Philosophy in Computing Science to ensure your application is passed to the correct team for processing.

Please clearly note the name of the lead supervisor and project titleon the application form. If you do not include these details, it may not be considered for the project.

Your application must include: A personal statement, an up-to-date copy of your academic CV, and clear copies of your educational certificates and transcripts.

Please note: you do not need to provide a research proposal with this application.

If you require any additional assistance in submitting your application or have any queries about the application process, please don't hesitate to contact us at researchadmissions@abdn.ac.uk

Funding Notes

This is a self-funding project open to students worldwide. Our typical start dates for this programme are February or October.

Fees for this programme can be found here Finance and Funding | Study Here | The University of Aberdeen