Hypusine modification of eIF5A by Deoxyhypusine Synthase (DHPS) is essential for the replication of a broad range of viruses, making DHPS an attractive host-directed therapy (HDT) target for antiviral drug discovery. AI-based drug design methods spanning binding affinity prediction and de novo molecular generation are rapidly proliferating, yet systematic benchmarking of diverse algorithmic paradigms under identical conditions on a shared target, with experimental validation, remains scarce. Here, we present an integrated AI benchmarking pipeline targeting DHPS and evaluate the full process from computational prediction to experimental validation. We compared 13 MM-GBSA score estimation models and 10 de novo molecular generation methods under 5-seed repeated experiments. For the prediction task, we propose an Out-of-Fold stacking ensemble integrating gradient boosting, graph neural networks, and chemical language models, achieving the highest Spearman rank correlation of 0.861 among all compared models. For the generation task, we propose RL-Design, a reinforcement learning-based framework using the ensemble predictor as a scoring oracle. RL-Design achieved the highest hit rate of 92.02% and maintained drug-like physicochemical properties across generated molecules, outperforming all nine competing methods. Moreover, experimental dose–response assays confirmed inhibitory activity in all three predicted-active compounds, with two highly active compounds showing IC50 values of 31.2 and 49.1 µM. Predicted and experimental activity showed complete concordance across all six tested compounds, providing oracle-independent validation of the pipeline. This pipeline provides a reproducible framework for AI-guided, target-specific inhibitor design and demonstrates the feasibility of HDT-focused antiviral drug discovery through systematic AI benchmarking.