For designing and evaluating reinforced concrete structures, it is essential to predict the punching shear strength (PSS) of fiber-reinforced polymer reinforced concrete (FRP-RC) beams. This study utilized three meta-heuristic improvement calculations — insect lion enhancer (ALO), moth fire analyzer (MFO), and salp swarm calculation (SSA) — to upgrade hyperparameters of an irregular timberland (RF) model for PSS expectation. The types of column section (TCS), cross-sectional area of the column (CAC), slab's effective depth (SED), span–depth ratio (SDR), compressive strength of concrete (CSC), yield strength of reinforcement (YSR), and reinforcement ratio (RR) were the seven characteristics of FRP-RC beams that were used as inputs. The ALO-RF model with a populace size of 100 exhibited unrivaled expectation execution: MAE of 25.0525, MAPE of 6.5696, R2 of 0.9820 in preparing, and MAE of 52.5601, MAPE of 15.5083, R2 of 0.941 in testing. SED's significant influence on PSS prediction suggests that it plays a crucial role in adjusting PSS. Additionally, the cross-breed AI model streamlined by metaheuristic calculations outperformed customary models in exactness and blunder control, featuring its true capacity for upgrading built up substantial construction plan and appraisal.