Master Thesis, 30 HP: Long-Term Memory Consolidation for Embodied Large Language Model Agents

Are you a student eager to apply your theoretical knowledge and fresh perspectives to real-world challenges? At Saab, we believe that innovation thrives on new ideas, and your master thesis project could be the spark that ignites our next technological breakthrough.

Your role

We recognize the immense value that students bring to our company. Your academic rigor, combined with your enthusiasm for cutting-edge technology, allows you to approach problems with a unique and insightful lens. At Saab, you'll have the opportunity to collaborate with experienced engineers and specialists, gaining invaluable practical experience while making a tangible contribution to our growth and development.

Background

The purpose of this thesis project is to investigate long-term memory mechanisms for embodied Large Language Model (LLM) agents, with a particular focus on episodic memory, memory consolidation, and forgetting. While existing agent memory systems primarily rely on retrieval-based approaches, recent research suggests that long-term intelligent behavior requires mechanisms that transform episodic experiences into more persistent, structured, and reusable knowledge.

Embodied LLM agents operating in dynamic environments must be able to remember past experiences, generalize from them, and adapt their behavior over extended periods of time. Although retrieval-based memory systems have demonstrated promising results, they often struggle with challenges related to scalability, interference, long-term retention, and effective knowledge abstraction. Drawing inspiration from human memory systems, approaches based on memory consolidation may enable agents to convert short-term experiences into more durable representations that support reasoning and decision-making across longer time horizons.

Description of the Thesis Project

The work will focus on evaluating how different strategies for storing, retrieving, consolidating, and forgetting experiences affect an embodied agent's ability to perform tasks in dynamic environments. Particular emphasis will be placed on understanding the trade-offs between memory capacity, retention, recall accuracy, interference resistance, and behavioral adaptation. The thesis will include a literature review of memory mechanisms for embodied and LLM-based agents, the implementation of a memory architecture supporting long-term memory consolidation, and evaluation in a simulated environment. Experiments will assess memory performance and agent behavior using benchmarks measuring recall accuracy, retention, interference resistance, spatial-temporal reasoning, and adaptation to changing conditions. The goal is to identify principles for scalable long-term memory systems that improve both memory performance and agent decision-making.

The thesis will be carried out together with Underwater Systems and the Mission Autonomy group at Saab Dynamics, which works on agentic intelligence and advanced autonomy solutions for future unmanned systems.

Your profile

You are in your final stage and have a educational background in Engineering Physics, Computer Science, AI/ML or equivalent and about to begin a 30 hp thesis project. We provide the support and guidance you need to translate your theoretical knowledge into practical solutions. Join us and become a driving force behind Saab's technological advancements!

This position requires that you pass a security vetting based on the current regulations around/of security protection. For positions requiring security clearance additional obligations on citizenship may apply.

Kindly observe that this is an ongoing recruitment process and that the position might be filled before the closing date of the advertisement.

What you will be a part of

Explore a wealth of possibilities. Take on challenges, create smart inventions, and grow beyond. This is a place for curious minds, brave pioneers, and everyone in between. Together, we achieve the extraordinary, each bringing our unique perspectives. Your part matters.

Saab is a leading defense and security company with an enduring purpose, to help nations keep their people and society safe. Empowered by its 28,000 talented people, Saab constantly pushes the boundaries of technology to create a safer and more sustainable world.

Saab designs, manufactures and maintains advanced systems in aeronautics, weapons, command and control, sensors and underwater systems. Saab is headquartered in Sweden. It has major operations all over the world and is part of the domestic defense capability of several nations. Read more about us here.