Groups of diverse problem solvers can outperform groups of high-ability problem solvers

TLDR

In large populations of problem solvers, the top performers tend to become similar, reducing diversity. The authors propose a framework for modeling functionally diverse agents and apply it to investigate how group composition affects performance. The framework represents agents with problem and algorithm representations that guide solution search. Randomly selected teams from a diverse pool outperform teams of the best agents, because high ability is outweighed by low diversity.

Abstract

We introduce a general framework for modeling functionally diverse problem-solving agents. In this framework, problem-solving agents possess representations of problems and algorithms that they use to locate solutions. We use this framework to establish a result relevant to group composition. We find that when selecting a problem-solving team from a diverse population of intelligent agents, a team of randomly selected agents outperforms a team comprised of the best-performing agents. This result relies on the intuition that, as the initial pool of problem solvers becomes large, the best-performing agents necessarily become similar in the space of problem solvers. Their relatively greater ability is more than offset by their lack of problem-solving diversity.