The cyclic injection of CO2, referred to as the huff-n-puff (HnP) method, is an attractive option to improve oil recovery from unconventional reservoirs. This study evaluates the optimization of the CO2 HnP method and provides insight into the aspects of CO2 sequestration for unconventional reservoirs. Furthermore, this study also examines the impact of nanopore confinement, fluid composition, injection solvent, diffusivity parameters, and fracture properties on the long-term recovery factor. The results from over 500 independent simulations showed that the optimal recovery is obtained for the puff-to-huff ratio of around 2.73 with a soak period of fewer than 2.7 days. After numerous HnP cycles, an optimized CO2 HnP process resulted in about 970-to-1067-ton CO2 storage per fracture and over 32% recovery, compared to 22% recovery for natural depletion over the 30 years. The optimized CO2 HnP process also showed higher effectiveness compared to the N2 HnP scenario. Additionally, for reservoirs with significant pore confinement (pore size ≤ 10 nm), the oil recovery improved by over 3% compared to the unconfined bulk phase properties. We also observed over 300% improvement in recovery factor for a fluid with a significant fraction of light hydrocarbons (C1−C6), compared to just a 50% improvement in recovery for a fluid with a substantial fraction of heavy hydrocarbons (C7+). Finally, the results also showed that fracture properties are much more important for CO2 HnP than natural depletion. This study provides critical insights to optimize and improve CO2 HnP operations for different fluid phases and fracture properties encountered in unconventional reservoirs.