发表机构
University of Pennsylvania; Shanghai Jiao Tong University; Meiji University（宾夕法尼亚大学; 上海交通大学; 明治大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出多层投票群体中集体智能进化的框架，证明单层投票无法解决非线性问题，并识别出“边际反馈”奖励结构，使群体通过个体模仿进化出等同于多层感知器的准确集体决策，为层级制度提供了进化解释。
AI 中文摘要
群体通过汇总意见，能够比任何单个成员更准确地解决集体问题。近期的理论工作已识别出个体层面的奖励方案，使得无知的个体能够通过社会学习，从底层逐步进化出集体智能。然而，这些结果仅限于线性预测问题和简单平均，而真实群体面临的决策任务往往是非线性的，且汇总意见的机构很少是单层平均：选区选举代表，代表再对政策投票；审稿人给编辑提供建议，编辑决定是否发表。在此，我们开发了一个多层投票群体中集体智能进化的框架，其中个体观察有限信息，群体通过多数规则递归汇总意见。我们证明，在任何个体奖励方案下，单层投票无法解决非线性分类问题。然后，我们识别出一种“边际反馈”的收益结构，该结构仅在个体的意见在其所在群体及每一上层中具有关键性时给予奖励。这种奖励方案促使分层群体仅通过个体层面的同伴模仿，就能进化出对复杂非线性决策任务的准确集体解决方案。所涌现的集体行为等同于机器学习中的多层感知器。我们的结果为层级制度提供了一种自然主义的解释，其中摇摆选民的超大重要性是维持集体准确性的激励；同时，我们将机器学习中的信用分配规则识别为不仅是工程解决方案，更是自然的进化结果。
英文摘要
Groups of individuals can solve collective problems more accurately than any single member, by aggregating their opinions. Recent theoretical work has identified individual-level reward schemes that allow uninformed individuals to evolve collective intelligence from the bottom up, through social learning. Yet these results are restricted to linear prediction problems and simple averaging, while the decision tasks that real groups confront are often non-linear, and the institutions that aggregate opinions are seldom single-layer averages: districts elect representatives who in turn vote on policy, referees advise editors who decide on publication. Here we develop a framework for the evolution of collective intelligence in multi-layer voting populations, where individuals observe limited information and groups recursively aggregate their opinions by majority rule. We prove that single-layer voting cannot solve non-linear classification problems under any individual reward scheme. We then identify a "marginal feedback" payoff structure, which rewards individuals only when their opinion is pivotal in their group, and at every layer above them. This reward scheme induces a layered population to evolve accurate collective solutions to complex, non-linear decision tasks through individual-level peer imitation alone. The collective behavior that emerges is equivalent to a multi-layer perceptron in machine learning. Our results provide a naturalistic account of hierarchical institutions, in which the outsize importance of swing voters is the incentive that sustains collective accuracy; and they identify the credit-assignment rule in machine learning as not just an engineered solution but a natural evolutionary outcome.
Comments39 pages, 4 figures. Supplementary materials (Materials and Methods, Supplementary Text, 12 supplementary figures) are appended to the main text
