Unbalanced battery cells are known to significantly degrade the performance and reliability of a large-scale battery sys- Tem. In this paper, we exploit emerging reconfigurable bat- Tery packs to mitigate the cell imbalance via the joint consid- eration of system reconfigurability and State-of-Health (So- H) of cells. Via empirical measurements and validation, we observe that a significantly larger amount of capacity can be delivered when cells with similar SoH levels are connected in series during discharging, which in turn extends the sys- Tem operation time. Based on this observation, we propose two SoH-aware reconfiguration algorithms focusing on fully and partially reconfigurable battery packs, and prove their (near) optimality. We evaluate the proposed SoH-aware re- configuration algorithms using both experiments and simu- lations. The algorithms are shown to deliver about 10-30% more capacity than SoH-oblivious configuration approaches.