Master Thesis – Agentic AI for Stimulus Creation During Coverage Closure

This thesis project explores how an Agentic AI solution can support stimulus creation during coverage closure for ASIC verification, aiming to reduce engineering effort and elapsed time while producing valid, reproducible tests. Two Master's students will work together to investigate state-of-the-art AI methods, establish benchmarks, tune the AI pipeline, and evaluate its effectiveness against manual solutions. The role focuses on adapting the AI pipeline around language models without requiring model-weight training or fine-tuning.