We examine whether regime-conditioned generative scenarios combined with a convex CVaR allocator improve portfolio decisions under regime shifts. We present MARCD, a generative-to-decision framework with: (i) a Gaussian HMM to infer latent regimes; (ii) a diffusion generator that produces regime-conditioned scenarios; (iii) signal extraction via blended, shrunk moments; and (iv) a governed CVaR epigraph quadratic program. Contributions: Within the Scenario stage we introduce a tail-weighted diffusion objective that up-weights low-quantile outcomes relevant for drawdowns and a regime-expert (MoE) denoiser whose gate increases with crisis posteriors; both are evaluated end-to-end through the allocator. Under strict walk-forward on liquid multi-asset ETFs (2005-2025), MARCD exhibits stronger scenario calibration and materially smaller drawdowns: MaxDD 9.3% versus 14.1% for BL (a 34% reduction) over 2020-2025 out-of-sample. The framework provides an auditable pipeline with explicit budget, box, and turnover constraints, demonstrating the value of decision-aware generative modeling in finance.

翻译：本研究探讨了体制条件生成情景与凸CVaR分配器相结合，是否能在体制转换下改善投资组合决策。我们提出了MARCD，一个从生成到决策的框架，包含：（i）用于推断潜在体制的高斯隐马尔可夫模型；（ii）生成体制条件情景的扩散生成器；（iii）通过混合收缩矩进行信号提取；以及（iv）受控的CVaR超图二次规划。贡献：在情景生成阶段，我们引入了一种尾部加权扩散目标，该目标对与回撤相关的低分位数结果赋予更高权重，以及一个体制专家（MoE）去噪器，其门控随危机后验概率增加而增强；两者均通过分配器进行端到端评估。在流动性多资产ETF（2005-2025年）的严格前向滚动测试下，MARCD展现出更强的情景校准能力和显著更小的回撤：2020-2025年样本外期间的最大回撤为9.3%，而基准模型BL为14.1%（减少34%）。该框架提供了一个可审计的流程，具有明确的预算、箱型和换手率约束，证明了决策感知生成建模在金融领域的价值。