In this paper, we propose \(\mathcal {H}\) -Efp, a Portfolio-like multi-agent epistemic planning solver that demonstrates scalability potential and tangible performance improvements compared to state-of-the-art epistemic multi-agent planning systems. Ultimately, our goal is to broaden the practical application of multi-agent epistemic reasoning in real-world scenarios by reducing resource demands, potentially enabling its use in modeling situations involving multiple entities sharing information, such as autonomous driving.