心智經濟：透過經濟互動湧現的多智能體智能

摘要

一群智能体如何在无中央控制的情况下，自我编排与自适应，形成更强大的集体智能？受弗里德里希·哈耶克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体来研究该问题——该经济体中智能体通过竞拍获取行动权、交换支付，并从环境奖励中积累财富。这些简单的经济信号催生了去中心化的信用分配机制，无需全局编排或显式通信协议即可驱动规划。智能体群体通过经济选择进化：高效智能体积累财富并通过开发机制发生变异，而低效智能体则破产并被探索机制所取代。我们证明，从弱智能体初始化开始，该经济体能够涌现出多步推理策略，并在五项智能体任务（包括数学推理、金融研究、科学研究、加速器设计与分布式系统优化）中超越更强的一体化基线模型。此外，我们提供了关于经济动态如何塑造智能体行为的理论洞见，将局部激励机制与长期全局表现相联系。我们的研究结果为多智能体智能开辟了新路径：与其设计协调机制，不如构建去中心化激励结构，使集体智能自动涌现。

English

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. 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. 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. 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.