Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions

思维经济：具有经济交互的涌现式多智能体智能

Abstract: How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedrich Hayek’s economic theory of decentralized coordination in markets, we study this question through an agent economy in which agents compete via auctions for the right to act, exchange payments, and accumulate wealth from environmental rewards.

摘要： 一个智能体群体如何在没有集中控制的情况下，自我协调并自我适应成更强大的集体智能？受弗里德里希·哈耶克（Friedrich Hayek）关于市场去中心化协调的经济理论启发，我们通过一个“智能体经济”模型研究了这一问题。在该模型中，智能体通过拍卖竞争行动权，进行支付交换，并从环境奖励中积累财富。

These simple economic signals induce decentralized credit assignment, driving planning without global orchestration or explicit communication protocols. The population evolves through economic selection: effective agents accumulate wealth and are mutated via exploitation, while ineffective ones go bankrupt and are replaced via exploration.

这些简单的经济信号诱导了去中心化的信用分配，从而在无需全局编排或显式通信协议的情况下驱动了规划过程。该群体通过经济选择进行演化：高效的智能体积累财富并通过开发（exploitation）进行变异，而低效的智能体则会破产，并通过探索（exploration）被替换。

We show that, initialized with weak agents, the economy produces emergent multi-step reasoning strategies and outperforms stronger monolithic baselines across five agentic tasks, including mathematical reasoning, financial research, scientific research, accelerator design, and distributed-system optimization.

我们证明，即使从弱智能体开始，该经济系统也能产生涌现的多步推理策略，并在包括数学推理、金融研究、科学研究、加速器设计和分布式系统优化在内的五项智能体任务中，超越了更强大的单一基准模型。

We further provide theoretical insights into how economic dynamics shape agent behaviors, linking local incentives to long-term global performance. Our results suggest a new path to multi-agent intelligence: rather than engineering coordination, we can design decentralized incentive structures under which it automatically emerges.

我们进一步提供了关于经济动态如何塑造智能体行为的理论见解，将局部激励与长期的全局表现联系起来。我们的研究结果为多智能体智能提供了一条新路径：与其通过工程手段设计协调机制，不如设计去中心化的激励结构，让协调机制在其中自动涌现。