An evolutionary origin of collective decision making in humans and machines

2026-10-05

AI Summary

This study addresses how collective intelligence emerges in multi-level populations through bottom-up social learning on nonlinear tasks. By integrating evolutionary game theory with multi-agent modeling, the authors construct a hierarchical voting framework and formally prove that single-layer mechanisms are insufficient for nonlinear classification. They subsequently propose a credit assignment reward mechanism based on marginal feedback to drive population evolution. This work reveals that such an incentive structure induces populations to spontaneously self-organize into collective intelligence resembling multilayer perceptrons, thereby offering a theoretical explanation for the natural origins of hierarchical systems. Furthermore, it establishes the pivotal role of key voters in sustaining collective accuracy, demonstrating that credit assignment in machine learning is fundamentally a product of natural evolution rather than merely an engineered solution.

Abstract

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.

Problem

• collective intelligence
• multi-layer voting
• non-linear decision tasks
• credit assignment
• evolutionary dynamics

Innovation

• collective intelligence
• multi-layer voting
• marginal feedback
• multi-layer perceptron
• credit assignment