AI-driven recruitment systems, while promising efficiency and objectivity, often perpetuate systemic inequalities by encoding cultural and social capital disparities into algorithmic decision making. This article develops and defends a novel theory of secondary bounded rationality, arguing that AI systems, despite their computational power, inherit and amplify human cognitive and structural biases through technical and sociopolitical constraints. Analyzing multimodal recruitment frameworks, we demonstrate how algorithmic processes transform historical inequalities, such as elite credential privileging and network homophily, into ostensibly meritocratic outcomes. Using Bourdieusian capital theory and Simon's bounded rationality, we reveal a recursive cycle where AI entrenches exclusion by optimizing for legible yet biased proxies of competence. We propose mitigation strategies, including counterfactual fairness testing, capital-aware auditing, and regulatory interventions, to disrupt this self-reinforcing inequality.

翻译：以人工智能驱动的招聘系统，虽承诺提升效率与客观性，却常通过将文化资本与社会资本差异编码至算法决策过程，延续了制度性不平等。本文提出并辩护了一种新颖的“二次有限理性”理论，论证人工智能系统尽管具备强大计算能力，仍通过技术与社会政治约束继承并放大了人类的认知与结构性偏差。通过分析多模态招聘框架，我们展示了算法进程如何将历史不平等（例如精英证书特权与网络同质性）转化为看似唯才是举的结果。借助布迪厄的资本理论与西蒙的有限理性理论，我们揭示了一种递归循环：人工智能通过优化那些清晰可辨但存在偏差的能力替代指标，进一步巩固了排斥机制。我们提出包括反事实公平性测试、资本感知审计与监管干预在内的缓解策略，以打破这种自我强化的不平等。