Exploring potential of OpenAI o3 as a signal-agnostic model for Signal/Background separation in $t \rightarrow uZ$ FCNC Searches at Future Hadron Colliders

Abstract: We present a case study exploring the potential of OpenAI's o3 model as a signal-agnostic tool for predicting optimized selection cuts in high-energy physics analyses. Specifically, we investigate the effectiveness of the model in separating signal from relevant Standard Model backgrounds in the context of Flavour-Changing Neutral Current (FCNC) top-quark couplings, focusing on the rare decay process $t \rightarrow uZ$. The study is performed at three collider setups: the approved High-Luminosity LHC (HL-LHC), the proposed High-Energy LHC (HE-LHC), and the Future Circular Collider in hadron-hadron mode (FCC-hh). We train the o3 model on detector level data for signal and background processes to predict selection cuts that enhance Signal-to-Background (S/B) discrimination. A comparative analysis is then carried out between the efficiencies resulting from o3-predicted cuts and those derived from traditional manually designed strategies used by a control group. Our results demonstrate that the o3 model performs on par with traditional methods in terms of S/B separation, with a slight improvement in the case of FCC-hh, suggesting its promise as a fast and generalizable tool for new physics searches.