A large share of retail investors hold public equities through mutual funds, yet lack adequate control over these investments. Indeed, mutual funds concentrate voting power in the hands of a few asset managers. These managers vote on behalf of shareholders despite having limited insight into their individual preferences, leaving them exposed to growing political and regulatory pressures, particularly amid rising shareholder activism. Pass-through voting has been proposed as a way to empower retail investors and provide asset managers with clearer guidance, but it faces challenges such as low participation rates and the difficulty of capturing highly individualized shareholder preferences for each specific vote. Randomly selected assemblies of shareholders, or ``investor assemblies,'' have also been proposed as more representative proxies than asset managers. As a third alternative, we propose artificial intelligence (AI) enabled representatives trained on individual shareholder preferences to act as proxies and vote on their behalf. Over time, these models could not only predict how retail investors would vote at any given moment but also how they might vote if they had significantly more time, knowledge, and resources to evaluate each proposal, leading to better overall decision-making. We argue that shareholder democracy offers a compelling real-world test bed for AI-enabled representation, providing valuable insights into both the potential benefits and risks of this approach more generally.

翻译：大量散户投资者通过共同基金持有公开股票，却对这些投资缺乏足够的控制权。事实上，共同基金将投票权集中在少数资产管理公司手中。这些管理者代表股东投票，却对股东的个人偏好知之甚少，使其日益暴露在增长的政治和监管压力之下，尤其是在股东积极主义兴起的背景下。传递投票（pass-through voting）已被提议作为赋能散户投资者并为资产管理公司提供更清晰指引的一种方式，但它面临着参与率低、难以捕捉每位股东对每次具体投票高度个性化偏好等挑战。随机选出的股东大会（或称“投资者大会”）也被提议作为比资产管理公司更具代表性的代理机制。作为第三种方案，我们提出基于人工智能的代理模型，该模型通过学习个体股东的偏好来作为代理并代表其投票。随着时间的推移，这些模型不仅能预测散户投资者在任一时刻会如何投票，还能预测若他们拥有更多时间、知识和资源来评估每项提案时可能会如何投票，从而实现更优的整体决策。我们认为，股东民主为人工智能代理提供了一个极具现实意义的试验场，能更广泛地揭示这种方法的潜在益处与风险。