In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet it often comes at the cost of decreased AI performance in areas of human strengths. This can inadvertently erode human trust and cause them to ignore AI advice precisely when it is most needed. Conversely, an aligned AI fosters trust yet risks reinforcing suboptimal human behavior and lowering human-AI team performance. In this paper, we start by identifying this fundamental tension between performance-boosting (i.e., complementarity) and trust-building (i.e., alignment) as an inherent limitation of the traditional approach for training a single AI model to assist human decision making. To overcome this, we introduce a novel human-centered adaptive AI ensemble that strategically toggles between two specialist AI models - the aligned model and the complementary model - based on contextual cues, using an elegantly simple yet provably near-optimal Rational Routing Shortcut mechanism. Comprehensive theoretical analyses elucidate why the adaptive AI ensemble is effective and when it yields maximum benefits. Moreover, experiments on both simulated and real-world data show that when humans are assisted by the adaptive AI ensemble in decision making, they can achieve significantly higher performance than when they are assisted by single AI models that are trained to either optimize for their independent performance or even the human-AI team performance.

翻译：在人机决策过程中，设计能够补充人类专业知识的AI一直是增强人机协作的自然策略，但这往往以降低AI在人类优势领域的性能为代价。这种设计可能无意中削弱人类信任，导致他们在最需要AI建议时忽略这些建议。相反，对齐的AI虽然能促进信任，却可能强化次优的人类行为并降低人机团队的整体性能。本文首先指出这种性能提升（即互补性）与信任建立（即对齐性）之间的根本矛盾，并将其视为传统训练单一AI模型辅助人类决策方法的固有局限。为克服这一局限，我们提出了一种新颖的人类中心自适应AI集成方法，该方法基于情境线索，通过优雅简洁且可证明接近最优的理性路由捷径机制，在两种专业AI模型——对齐模型与互补模型——之间进行策略性切换。全面的理论分析阐明了自适应AI集成为何有效以及在何种条件下能产生最大效益。此外，在模拟数据和真实数据上的实验表明，当人类在决策过程中获得自适应AI集成的辅助时，其表现显著优于仅使用单一AI模型辅助的情况——即使这些单一模型经过训练以优化其独立性能甚至人机团队性能。