With the rapid development of large language models (LLMs), machine-generated texts have approached human writing quality, leading to four main text categories: purely machine-generated, machine-rewritten, machine-polished, and human-written content. Traditional detection methods face significant challenges in human-machine hybrid scenarios where LLMs perform rewriting or polishing, as existing approaches focus on single-level features and fail to capture subtle, multi-layered machine traces. To address this limitation, we propose a Multi-level Style Preference Optimization (MSPO) framework that captures machine-generated style features across multiple granularities: sequence-level optimization evaluates overall text style consistency, phrase-level detection identifies distinctive n-gram patterns, and lexical-level modeling captures word selection differences through probability distribution analysis. We further incorporate four text complexity indicators (Type-Token Ratio, Average Sentence Length, Average Word Length, and Punctuation Ratio) to dynamically adjust optimization parameters based on human-machine text complexity differences, enhancing adaptability across diverse text types. Additionally, we construct a comprehensive detection dataset spanning three representative domains (scientific writing, news, and creative writing) across four text types (human-written, purely machine-generated, machine-rewritten, and machine-polished), generated using state-of-the-art LLMs for robust evaluation. Experimental results demonstrate that MSPO significantly outperforms existing methods across generated, rewritten, and polished text detection tasks, with the most notable improvement of 0.156 AUROC points over baseline ImBD on challenging polished texts, while maintaining robust cross-domain generalizability.