The analysis of particle collisions at the Large Hadron Collider at CERN helps us to understand the fundamental building blocks of our universe. After years of data taking, the extraction of fundamental insights often requires intricate data analyses. Due to the large volume and complex structure of the data, these necessitate advanced and powerful analysis techniques.
We will explore typical data structures in high-energy physics and point out specific challenges. Focusing on two main tasks in current analyses, we introduce innovative methods designed to overcome these. The first challenge involves using graph-based learning techniques for particle reconstruction. The second challenge leverages reinforcement learning methods for particle identification.
Throughout the presentation, we will examine how these cutting-edge methods can be incorporated into contemporary high-energy physics data analysis and touch on their potential application in other scientific domains.