Cooperative multi-agent reinforcement learning (Co-MARL) commonly employs different parameter sharing mechanisms, such as full and partial sharing. However, imprudent application of these mechanisms can potentially constrain policy diversity and limit cooperation flexibility. Recent methods that group agents into distinct sharing categories often exhibit poor performance due to challenges in precisely differentiating agents and neglecting the issue of promoting cooperation among these categories. To address these issues, we introduce a dynamic selective parameter sharing mechanism embedded with multi-level reasoning abstractions (DSPS-MA). Our approach uses self-comparison sequences to infer agents’ abstract concepts, defining the differences between agents and allowing them to dynamically select partners to share parameters based on these abstract concepts. We also design an intrinsic reward to offer comprehensive collaboration guidance for agents, and introduce a policy cosine similarity regularization term to ensure sufficient policy diversity. Empirical evaluations demonstrate that our approach yields higher returns and faster convergence than state-of-the-art methods.