Master Thesis: Interaction-Derived Knowledge Bases for Self-Improving UI Agents

Your Profile

• Currently pursuing aMaster’s degree in Computer Scienceor a related field with strong academic performance
• excellentprogramming skills in Python
• proven hands-on experience working withLarge Language Models (LLMs) and popular LLM frameworks and tooling (e.g., LangChain, Hugging Face, PyTorch, …)
• profound experience designing or working withagentic AI systems
• ability to work independently, think analytically, and structure complex problems
• very good English skills (written and spoken)
• based in Germany

• Prior experience withRetrieval-Augmented Generation (RAG)or other memory-augmented LLM architectures
• experience with experimental evaluation or applied research in AI / ML
• first experience with writing or publishing scientific papers
• German language skills are helpful, but not required

Our Offer

• close collaboration and supportive mentoring with fast feedback cycles, while giving you the freedom to explore your own ideas and drive your work independently
• work with a team that combines strong research expertise with a hands-on, product-driven mindset on bleeding edge AI systems that are used by companies worldwide
• opportunity to have a high and lasting impact on product, company and people
• Choose how you want to work: Fully remote, in our office in Karlsruhe or hybrid
• Flexible working hours
• A place where you are valued not only for you expertise but also as a human as part of a team where most consider each other not only to be a colleagues but friends

Your Role

Background and Goal of the Thesis When humans interact with unfamiliar UIs, they rarely succeed to accomplish a task immediately. Instead, they explore, make mistakes, and gradually build an understanding of how tasks can be completed efficiently in the UI. This allows them to navigate UIs more directly over time, and avoid previous errors. In contrast, LLM-based agents that operate UIs, yet lack the ability to systematically accumulate and reuse knowledge gained from previous interactions and hence improve over time. As a result, they keep repeating inefficient behaviors and fail to improve over time. The goal of this thesis is toenable UI Agents tolearn from their own past interactions by designing a continuously updated knowledge base. The agent should store and refine knowledge about UI structures, action outcomes, navigation paths, and discovered functionality, and leverage this knowledge in future interactions. This includes remembering efficient workflows for recurring tasks as well as observations that may become relevant in different contexts later.

Your Responsibilities

• conduct a comprehensive literature review on existing work and state-of-the-art methods
• explore and design novel approaches to the problem
• develop and implement prototypes or experimental systems to validate proposed ideas
• define and conductexperiments and evaluations to assess performance, robustness, and limitations
• continuously present your work in team presentations and written reports
• collaborate closely with researchers and engineers to align research outcomes with real-world applications

Apply Now!

Join our mission!