Strategies for orchestrating the interactions between multiple agents, both human and artificial, can wildly overestimate performance and underestimate the cost of orchestration. We design a framework to orchestrate agents under realistic conditions, such as inference costs or availability constraints. We show theoretically that orchestration is only effective if there are performance or cost differentials between agents. We then empirically demonstrate how orchestration between multiple agents can be helpful for selecting agents in a simulated environment, picking a learning strategy in the infamous Rogers' Paradox from social science, and outsourcing tasks to other agents during a question-answer task in a user study.

翻译：协调多智能体（包括人类与人工智能体）交互的策略，往往严重高估其性能表现并低估协调成本。我们设计了一个在现实条件下（如推理成本或可用性约束）协调智能体的框架。理论上，我们证明仅当智能体之间存在性能或成本差异时，协调机制才具有实效。随后，我们通过实证研究展示了多智能体协调在以下场景中的有效性：在模拟环境中进行智能体选择、在社会科学中著名的罗杰斯悖论中选取学习策略，以及在一项用户研究的问答任务中向其他智能体外包任务。