The widespread dissemination and societal impact of fake news underscore the critical need for effective detection. Existing methods remain limited, as they often fail to learn joint representations from multi-modal data and rely heavily on complete social interaction signals. Such information is frequently unavailable in practice, especially during the early propagation stages. To address early fake news detection in social media, this paper proposes a hierarchical cross-modal fusion framework with structured LLM-simulated social interaction (HCF-LSIM). The framework employs a progressive cross-modal attention mechanism to systematically align semantic representations across multiple levels, integrating textual, thematic, and visual features. Additionally, HCF-LSIM designs an LLM-powered social interaction simulator that generates structured triplets from adapted user profiles, effectively compensating for missing real-time interaction data. Experiments on public benchmarks demonstrate strong performance, with accuracies of 93.5% on Weibo and 87.2% on X (formerly Twitter), ranking first on Weibo and second on Twitter.