This paper explores the use of machine-learned interatomic potentials (MLIPs) to improve the efficiency of crystal structure prediction (CSP) in organic materials. The authors investigate active learning methods to train MLIPs using CSP datasets, combining them with well-developed sampling methods from CSP to create highly automated workflows that are relevant over a wide range of crystal packing spaces. The study demonstrates how these potentials can efficiently rerank large, diverse crystal structure landscapes to near-DFT accuracy, improving the reliability of energy rankings. Additionally, the potentials are extended to accurately model structures far from lattice energy minima through on-the-fly training within Monte Carlo simulations. The workflow is applied to two challenging systems, triptycene-tris-(benzimidazolone) (TTBI) and resorcinol, showing significant improvements in energy rankings and accuracy. The results highlight the potential of MLIPs for efficient and accurate crystal structure prediction in organic materials.This paper explores the use of machine-learned interatomic potentials (MLIPs) to improve the efficiency of crystal structure prediction (CSP) in organic materials. The authors investigate active learning methods to train MLIPs using CSP datasets, combining them with well-developed sampling methods from CSP to create highly automated workflows that are relevant over a wide range of crystal packing spaces. The study demonstrates how these potentials can efficiently rerank large, diverse crystal structure landscapes to near-DFT accuracy, improving the reliability of energy rankings. Additionally, the potentials are extended to accurately model structures far from lattice energy minima through on-the-fly training within Monte Carlo simulations. The workflow is applied to two challenging systems, triptycene-tris-(benzimidazolone) (TTBI) and resorcinol, showing significant improvements in energy rankings and accuracy. The results highlight the potential of MLIPs for efficient and accurate crystal structure prediction in organic materials.