Current air combat decision methods mostly lack structured adversarial validation and adaptive reflection mechanisms, limiting their robustness and reliability when facing deceptive or unfamiliar enemy strategies. To address this, we propose the Adversarial Iterative Pre-Enactment (AIP) framework, which integrates cognitive mental simulation with a large language model. First, we design a self-adversarial pre-enactment–feedback loop that enables the model to simulate and evaluate both friendly and enemy actions before execution. Second, we introduce a multiscale segmented evaluation mechanism that analyzes tactical effectiveness across different time horizons and perspectives. Third, we build a high-fidelity simulation environment with scenario rewind capability, enabling real-time dual-strategy execution and supporting structured adversarial evaluation. Experimental results demonstrate the superiority of AIP over standard LLM baselines in terms of both tactical score and stability under complex adversarial conditions.