Enhancing the OMTF Trigger for Phase-2 with a GNN

This poster presents our work to interpret track segments (stubs) from the muon detectors as nodes of a graph, analyze their structure, and reconstruct the muon trajectory using a Graph Neural Network (GNN). As a case study, we focus on the barrel-endcap transition region of the CMS experiment. This GNN also aims at the reduction of computing time, allowing for the integration within the upgraded hardware-level trigger. A preliminary implementation on firmware will also be discussed. The GNN model is being adapted for targeting also displaced muon signatures to potentially enhance searches for long-lived particles. This poster was presented at the 7th Inter-Experimental LHC Machine Learning Workshop (19–23 May 2025, CERN).